© 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. 46298
    Prev
    Next
    INDEX
    Explanations

    roles and descriptions

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

    API access

    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
     probabilidad
    0.55
    龅
    0.48
    ည့်
    0.47
     neemt
    0.46
     elegir
    0.45
     índice
    0.45
     posición
    0.45
    ను
    0.44
    为例
    0.44
     último
    0.43
    POSITIVE LOGITS
    몰
    0.47
    cumin
    0.45
    сі
    0.43
    וו
    0.43
     molle
    0.43
    옷
    0.43
    StringBuilder
    0.42
    brough
    0.42
    ಿಯಾಗ
    0.42
    TestAction
    0.42
    Activations Density 0.000%

    No Known Activations