© 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. 238036
    Prev
    Next
    INDEX
    Explanations

    spectacular related words and sequences

    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
    ;,
    0.45
    file
    0.44
    datei
    0.43
    inox
    0.41
    operation
    0.41
    CrossRef
    0.41
    date
    0.40
    ;',
    0.40
    ,)
    0.39
    registry
    0.38
    POSITIVE LOGITS
     espectacular
    0.51
     authenticate
    0.46
     protagonistas
    0.46
     Spectacular
    0.45
    ждый
    0.45
     podrán
    0.44
     nacionais
    0.44
    戏剧
    0.43
     protagonista
    0.43
    சித்த
    0.43
    Activations Density 0.000%

    No Known Activations