© 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. 93639
    Prev
    Next
    INDEX
    Explanations

    Número o tipo de item

    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
     those
    -1.09
     people
    -0.98
     even
    -0.92
     both
    -0.91
     at
    -0.86
     that
    -0.85
     just
    -0.84
    Thiết
    -0.83
     Those
    -0.81
     Usually
    -0.81
    POSITIVE LOGITS
     curio
    1.11
    Curi
    0.98
     doctrina
    0.97
     specta
    0.95
     gastronom
    0.94
     McDonalds
    0.93
     MEGA
    0.93
     mafia
    0.92
     Leona
    0.90
     tupperware
    0.90
    Activations Density 0.003%

    No Known Activations