© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31895
    Prev
    Next
    INDEX
    Explanations

    alerts and summaries

    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
     finalized
    -0.81
     Vielzahl
    -0.81
    elashes
    -0.81
     Merkmale
    -0.78
     Lordship
    -0.74
    syd
    -0.74
    Delhi
    -0.73
     Examiner
    -0.73
    ेशन
    -0.71
    ticello
    -0.71
    POSITIVE LOGITS
    jesz
    0.84
    ご予約
    0.83
    митри
    0.79
     alte
    0.77
    IZO
    0.75
     cảnh
    0.74
    ၇
    0.73
    美術館
    0.72
    ＊＊＊
    0.72
     تهیه
    0.71
    Activations Density 0.010%

    No Known Activations