© 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. 65798
    Prev
    Next
    INDEX
    Explanations

    regional championships

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

    code snippets and programming terms

    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
     Secret
    0.48
     Secretaries
    0.44
    Secret
    0.44
    ⸝
    0.43
     chevaux
    0.43
    เหล
    0.42
     onPress
    0.42
    ม่
    0.42
     είχε
    0.42
     архівної
    0.42
    POSITIVE LOGITS
    ag
    0.50
     otros
    0.48
    ?
    0.48
    ms
    0.48
    ướ
    0.48
    vol
    0.47
     Otros
    0.47
    l
    0.47
    udir
    0.46
     calific
    0.46
    Activations Density 0.001%

    No Known Activations