© 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. 21108
    Prev
    Next
    INDEX
    Explanations

    camping

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

    The neuron is essentially a “camping detector,” strongly activating on the word “camping” (and closely related forms like “campers”) in the text.

    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
    梛
    -2.47
     Exteriores
    -2.47
     髪型
    -2.44
    缡
    -2.42
    峮
    -2.42
     behöver
    -2.34
    饧
    -2.33
    所以在
    -2.28
    髕
    -2.27
    
    -2.23
    POSITIVE LOGITS
    ,”
    3.53
    y
    3.23
    c
    3.11
    ↵↵
    3.08
    d
    2.94
    i
    2.94
    )
    2.86
    </strong>
    2.81
    -
    2.70
     If
    2.61
    Activations Density 0.008%

    No Known Activations