© 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. 193485
    Prev
    Next
    INDEX
    Explanations

    athletes, Ohio, shock, love, securing

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

    amp circuit

    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
    ΕΣ
    0.51
     Sampson
    0.48
    使い
    0.46
     Κα
    0.44
     Octopus
    0.44
     Resolución
    0.44
    ষ্টার
    0.44
    恵
    0.44
    트로
    0.43
     AMP
    0.43
    POSITIVE LOGITS
     वेळी
    0.48
    alary
    0.48
    ी
    0.47
    ineda
    0.47
    quisite
    0.46
    aval
    0.46
    ala
    0.44
    ual
    0.44
    una
    0.44
    ork
    0.44
    Activations Density 0.000%

    No Known Activations