© 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. 121156
    Prev
    Next
    INDEX
    Explanations

    first items and conditions

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

    first or largest

    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
    疽
    0.48
    区间
    0.46
    豁
    0.45
    гро
    0.45
    回头
    0.45
    ágico
    0.45
    ИС
    0.45
    写
    0.45
    鸷
    0.44
    periode
    0.43
    POSITIVE LOGITS
     pertama
    0.46
     only
    0.46
     ensimmä
    0.46
     first
    0.45
     First
    0.45
     solves
    0.45
     Pierws
    0.44
     largest
    0.43
     första
    0.43
    ’
    0.42
    Activations Density 0.000%

    No Known Activations