© 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. 100286
    Prev
    Next
    INDEX
    Explanations

    upside down or orientation

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

    The neuron specifically detects occurrences of the word “upside.”

    oai_token-act-pair · o4-miniTriggered 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
    >
    -3.58
    ).
    -2.94
    );
    -2.88
    la
    -2.70
    m
    -2.69
    /
    -2.56
    (
    -2.56
    0
    -2.47
    蠵
    -2.42
    n
    -2.38
    POSITIVE LOGITS
     ſte
    3.03
     ſta
    2.84
    ſelf
    2.75
    
    2.66
    ꔹ
    2.61
    ឵
    2.56
     empower
    2.50
    ￬
    2.47
    ଢ
    2.42
    鋱
    2.41
    Activations Density 0.001%

    No Known Activations