© 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. 34-GEMMASCOPE-RES-131K
    7. 103747
    Prev
    Next
    INDEX
    Explanations

    of any kind

    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
    *}
    -0.96
     polícia
    -0.93
    💗
    -0.92
    ஶ
    -0.91
    sians
    -0.85
    []}
    -0.83
    eeeeeeee
    -0.82
    "]/
    -0.81
     glyphicon
    -0.81
    makeText
    -0.81
    POSITIVE LOGITS
    Udo
    0.80
     Appe
    0.72
     invol
    0.71
     EXACTLY
    0.71
    ことの
    0.69
     marred
    0.69
    僕も
    0.68
     Betrag
    0.67
    влека
    0.67
     bật
    0.67
    Activations Density 0.003%

    No Known Activations