© 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. 15930
    Prev
    Next
    INDEX
    Explanations

    ISBN, attention, values

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

    BIOS or UEFI boot settings

    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
    🅾
    0.44
    gewood
    0.42
    startswith
    0.41
    ępuje
    0.41
    ͕
    0.40
    orElse
    0.40
    sylvania
    0.39
    ;
    0.39
    ana
    0.39
    aga
    0.39
    POSITIVE LOGITS
     coefficients
    0.49
    $:
    0.49
     valores
    0.47
    ួក
    0.47
     mensagens
    0.46
     pouvaient
    0.46
     respectivos
    0.45
    質量
    0.45
     perilaku
    0.44
     davranış
    0.44
    Activations Density 0.000%

    No Known Activations