© 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. 69532
    Prev
    Next
    INDEX
    Explanations

    word completion or continuation

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

    calculating expected value

    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
     Himalaya
    0.48
     Attach
    0.47
     Various
    0.46
    м
    0.46
     onay
    0.45
     Var
    0.45
     july
    0.45
     Converting
    0.45
     By
    0.44
     Author
    0.43
    POSITIVE LOGITS
    chio
    0.47
    situ
    0.46
    摄像
    0.46
    辨
    0.46
    mapStateToProps
    0.45
    ಂಥ
    0.44
     ঘটেছে
    0.44
     جال
    0.44
    座
    0.43
     เด้อ
    0.43
    Activations Density 0.000%

    No Known Activations