© 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. 197
    Prev
    Next
    INDEX
    Explanations

    explorers and authors

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

    focuses on, free from, whenever he

    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
    ഒരു
    0.25
    唦
    0.24
    करण
    0.24
     Komponenten
    0.24
     Benutz
    0.23
     Objekte
    0.23
    唥
    0.23
    畛
    0.23
     سافٹ
    0.23
     adresu
    0.23
    POSITIVE LOGITS
     from
    0.29
    1
    0.28
    <0xC2>
    0.27
     (
    0.26
     [
    0.24
    （
    0.24
     metaverse
    0.24
    ,[
    0.23
    ”（
    0.23
     I
    0.23
    Activations Density 14.229%

    No Known Activations