© 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. 242215
    Prev
    Next
    INDEX
    Explanations

    birth parent

    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
    ле
    0.54
    ون
    0.50
    و
    0.50
    設備
    0.50
     স্বয়ং
    0.47
    ১
    0.47
     القلب
    0.46
     죽
    0.46
    тику
    0.46
     قلب
    0.45
    POSITIVE LOGITS
     candid
    0.52
     predecess
    0.51
     Carrie
    0.50
     caric
    0.50
     assembled
    0.50
     anteced
    0.47
    azine
    0.47
     demost
    0.47
     predicted
    0.46
     adoptive
    0.46
    Activations Density 0.000%

    No Known Activations