© 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. 245354
    Prev
    Next
    INDEX
    Explanations

    month, date, match, friend

    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
    ުރ
    0.54
    於
    0.53
    ك
    0.51
    trade
    0.50
    Catal
    0.50
    trav
    0.50
    عين
    0.49
    tax
    0.48
    hot
    0.47
    heaven
    0.47
    POSITIVE LOGITS
    밂
    0.57
     gelap
    0.52
     MDLVertex
    0.52
    áni
    0.51
     immunoblot
    0.50
    കേന്ദ്രം
    0.49
     यंदा
    0.49
     मिळू
    0.49
    āra
    0.48
    釭
    0.48
    Activations Density 0.000%

    No Known Activations