© 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. 6559
    Prev
    Next
    INDEX
    Explanations

    actions and descriptions

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

    remarkable development and expansion

    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
    *.
    0.97
    。
    0.95
    ".
    0.91
    ).
    0.88
    %.
    0.86
    _.
    0.84
    '.
    0.84
    .}
    0.82
    .
    0.82
     :).
    0.82
    POSITIVE LOGITS
     없고
    0.83
    했고
    0.81
     અને
    0.69
     এবং
    0.68
    的同时
    0.66
     และ
    0.65
     있으며
    0.64
     आणि
    0.63
     уйнагыз
    0.63
    并通过
    0.63
    Activations Density 0.129%

    No Known Activations