© 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. 96517
    Prev
    Next
    INDEX
    Explanations

    goods and services

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

    following descriptions

    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
     푸
    0.47
    independent
    0.42
     पुरु
    0.41
     Topological
    0.41
     좌표
    0.41
    ੁ
    0.41
    ாச
    0.41
     닮
    0.40
    荸
    0.40
     ನೇ
    0.40
    POSITIVE LOGITS
     emanating
    0.46
    ريق
    0.43
    我們會
    0.43
     pourront
    0.42
    減少
    0.41
     diverge
    0.41
    昅
    0.41
    員の
    0.41
     momentum
    0.40
    場の
    0.40
    Activations Density 0.001%

    No Known Activations