© 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. 71681
    Prev
    Next
    INDEX
    Explanations

    post followed by date, month, or description

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

    share information or insights

    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
    avali
    0.53
     শঙ্ক
    0.47
    鴳
    0.47
    סטר
    0.47
    MnO
    0.47
    stone
    0.46
    awatir
    0.46
    氐
    0.46
     சனி
    0.46
    perceptron
    0.46
    POSITIVE LOGITS
     combined
    0.54
     referring
    0.51
     bilinear
    0.51
     workaround
    0.49
     ejecut
    0.49
     combo
    0.47
     director
    0.47
     opposing
    0.47
     combination
    0.46
     sporting
    0.46
    Activations Density 0.000%

    No Known Activations