© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40087
    Prev
    Next
    INDEX
    Explanations

    photoshoot editorial sessions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on the word “shoot” (and its inflections like “shoots” and “shooting”), especially in the context of photo or video shoots.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to photography or video shoots, especially in fashion/editorial or studio contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "shoot" or "shoots" in the context of photography and fashion photo sessions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    );
    -1.78
    喽
    -1.73
     to
    -1.53
    
    -1.53
    ):
    -1.47
    ཋ
    -1.46
    𖡼
    -1.46
    』、
    -1.46
    犰
    -1.45
     It
    -1.45
    POSITIVE LOGITS
    蹰
    1.74
     ------
    1.72
    </strong>
    1.71
    っていたので
    1.62
    甞
    1.59
     impresionantes
    1.59
     eas
    1.58
     
    1.58
     ethic
    1.57
     photoshoot
    1.56
    Activations Density 0.008%

    No Known Activations