© 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. 164527
    Prev
    Next
    INDEX
    Explanations

    research organization or circulation enzymes

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

    formal & comprehensive

    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
    濑
    0.53
     ሁኔታ
    0.52
     सोमवार
    0.50
    恸
    0.50
     ሌሎች
    0.50
    蕎
    0.49
    惆
    0.48
    篾
    0.48
    醿
    0.48
     সোমবার
    0.48
    POSITIVE LOGITS
    t
    0.59
    ati
    0.58
     inv
    0.55
    ate
    0.54
    ing
    0.53
    st
    0.53
     at
    0.53
     and
    0.52
     can
    0.52
     for
    0.52
    Activations Density 0.001%

    No Known Activations