© 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. 76610
    Prev
    Next
    INDEX
    Explanations

    names of historical entities

    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
    があり
    -1.04
    それにしても
    -1.03
    最近は
    -0.98
    最後は
    -0.97
    写真は
    -0.96
    もちろん
    -0.92
     specifics
    -0.92
    galkan
    -0.90
     Grüßen
    -0.89
    写真の
    -0.88
    POSITIVE LOGITS
    デア
    1.00
    ֻ
    0.91
    によく
    0.90
    際には
    0.89
    際は
    0.89
    ТОВ
    0.88
     espirituales
    0.88
    づけ
    0.88
    andafter
    0.85
    الب
    0.84
    Activations Density 0.113%

    No Known Activations