© 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. 18494
    Prev
    Next
    INDEX
    Explanations

    penalties all, a boat

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

    asking questions and providing help

    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
    ુ
    0.53
    лина
    0.51
    Linki
    0.49
    ના
    0.47
    כה
    0.47
    ión
    0.47
    ंशी
    0.47
    ים
    0.46
    ು
    0.46
    Keyword
    0.46
    POSITIVE LOGITS
     simonsen
    0.47
     juin
    0.46
     propelled
    0.46
     controvers
    0.46
     mirac
    0.45
    {,}
    0.44
     dissolve
    0.43
     barba
    0.43
     universities
    0.43
     bart
    0.43
    Activations Density 0.000%

    No Known Activations