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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60723
    Prev
    Next
    INDEX
    Explanations

    skin

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

    references to skins, particularly in software/website contexts and file paths.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on occurrences of the substring “skin” (and its variants like “skins”) in product names, directory names, or file-path tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     calcetines
    -0.86
    Sozial
    -0.85
     заре
    -0.81
     sportif
    -0.80
     Strikes
    -0.78
     Tavares
    -0.77
     gbc
    -0.74
     akumulator
    -0.73
     terapi
    -0.73
     sampah
    -0.73
    POSITIVE LOGITS
    Skin
    1.01
     Skin
    0.91
     Sk
    0.85
    Kin
    0.84
    Sk
    0.81
    >_
    0.80
     populist
    0.80
    เที่ยว
    0.79
    aire
    0.77
    ія
    0.76
    Activations Density 0.011%

    No Known Activations