© 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. 11965
    Prev
    Next
    INDEX
    Explanations

    comma or parenthesis followed by specific word

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

    VIP treatment, spanned centuries

    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
    스럽
    0.45
    ски
    0.45
    جي
    0.43
    pulsewidth
    0.43
    ([])
    0.42
     (
    0.41
    스러운
    0.41
    عي
    0.41
    Translate
    0.40
    obra
    0.39
    POSITIVE LOGITS
     menilai
    0.49
    遗憾
    0.48
     hanno
    0.47
     dentre
    0.46
    ‛
    0.46
     мають
    0.45
     istilah
    0.45
     секре
    0.43
     статус
    0.43
     Ispol
    0.42
    Activations Density 0.000%

    No Known Activations