© 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. 110792
    Prev
    Next
    INDEX
    Explanations

    donation acquisition or most important

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

    scientific classification or description

    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
     važ
    0.55
     ২৭
    0.52
    𝗿
    0.49
     कोणता
    0.47
     други
    0.46
     Ked
    0.46
     altro
    0.46
     مطم
    0.45
     без
    0.45
     condi
    0.45
    POSITIVE LOGITS
    Statement
    0.51
    Dallas
    0.46
    Indianapolis
    0.46
    class
    0.45
    (*
    0.44
    ovou
    0.42
    ographiques
    0.42
    Montreal
    0.41
     मंदिरों
    0.41
    Coins
    0.40
    Activations Density 0.001%

    No Known Activations