© 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. 11198
    Prev
    Next
    INDEX
    Explanations

    object id assignments

    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
     «
    -0.97
    なども
    -0.97
     etc
    -0.95
    ª
    -0.93
    patterns
    -0.91
     而
    -0.88
    関する
    -0.88
     „
    -0.88
     WaitForSeconds
    -0.86
     Which
    -0.86
    POSITIVE LOGITS
     gustar
    1.02
    Зно
    1.02
    を選び
    0.98
     eclip
    0.93
     reír
    0.92
     siè
    0.92
    ⅖
    0.91
    Noe
    0.91
     maux
    0.91
     alasan
    0.90
    Activations Density 0.008%

    No Known Activations