© 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. 22-GEMMASCOPE-RES-131K
    4. 39330
    Prev
    Next
    INDEX
    Explanations

    code elements like `window`, `TextView`, `();`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    варь
    -0.84
     must
    -0.79
     kurikulum
    -0.77
    vidas
    -0.77
    TERNS
    -0.75
     Már
    -0.75
    gettimeofday
    -0.75
     involunt
    -0.74
    ziert
    -0.74
    labus
    -0.73
    POSITIVE LOGITS
    lacoste
    0.89
     drenaje
    0.85
    rdı
    0.82
    *}\
    0.82
     tẩy
    0.81
    valentino
    0.81
    realme
    0.80
     peinture
    0.80
     czerw
    0.79
    hindu
    0.79
    Activations Density 0.017%

    No Known Activations