© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 115633
    Prev
    Next
    INDEX
    Explanations

    help people

    np_acts-logits-general · gemini-2.5-flash-lite

    . ExampleThispoint is 4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🥟
    0.49
    嬉しい
    0.46
    🧒
    0.45
    HZ
    0.45
    FundMe
    0.44
    ELY
    0.44
    贈
    0.44
     以上
    0.44
     tattooing
    0.42
    াদে
    0.42
    POSITIVE LOGITS
     गया
    0.47
     conversación
    0.46
     लेसन
    0.45
    婼
    0.45
     команды
    0.45
    琬
    0.44
     Distinction
    0.43
     didn
    0.42
    震撼
    0.42
    ंकन
    0.42
    Activations Density 0.000%

    No Known Activations