© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68808
    Prev
    Next
    INDEX
    Explanations

    code block punctuation

    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
     it
    -0.88
     debate
    -0.84
    setViewName
    -0.82
     even
    -0.81
    */
    -0.81
    他
    -0.81
     неизвест
    -0.80
    )>>
    -0.80
    music
    -0.80
    ية
    -0.80
    POSITIVE LOGITS
    tasche
    0.96
    一張
    0.85
    ついでに
    0.84
    可爱的
    0.84
     Same
    0.83
    另一种
    0.82
    こっち
    0.80
    Holger
    0.79
    側に
    0.79
    momento
    0.79
    Activations Density 0.039%

    No Known Activations