© 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. 83712
    Prev
    Next
    INDEX
    Explanations

    legal citation and licenses

    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_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
     qualcosa
    -0.84
    🦲
    -0.78
     fonder
    -0.77
    INGRED
    -0.77
    Regel
    -0.75
    ulink
    -0.75
     говорю
    -0.74
    垃
    -0.74
     fray
    -0.73
    ทั้งหมด
    -0.73
    POSITIVE LOGITS
     c
    1.19
    Center
    0.82
    c
    0.82
    コピー
    0.78
     chữa
    0.78
    "@
    0.75
    蝠
    0.75
     center
    0.75
     pouring
    0.75
    ICC
    0.75
    Activations Density 0.002%

    No Known Activations