© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2965
    Prev
    Next
    INDEX
    Explanations

    Git Release, SD Document, AB Group, EC Application, Orchid Resource, RTC Member, My Line

    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
    不错
    -0.93
     такъ
    -0.93
    responder
    -0.93
    太多
    -0.93
     fröh
    -0.90
    manteau
    -0.89
    พาะ
    -0.89
    ピッタリ
    -0.88
    auta
    -0.87
     geringen
    -0.87
    POSITIVE LOGITS
    <?>>
    1.16
    Object
    1.10
    Simple
    0.98
    }}{\
    0.96
    Multi
    0.95
    ="<?=
    0.94
    وقع
    0.94
     вашим
    0.91
    issen
    0.91
    Easy
    0.91
    Activations Density 0.103%

    No Known Activations