© 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. 46761
    Prev
    Next
    INDEX
    Explanations

    Kurt muffin

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

    file types or extensions

    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
    ktiv
    0.51
    usually
    0.48
    of
    0.46
    ਵਾ
    0.44
    ranging
    0.44
    у
    0.43
    factual
    0.42
    urge
    0.42
    蛻
    0.42
    let
    0.41
    POSITIVE LOGITS
     referente
    0.47
    ",[],
    0.44
    স্‌
    0.44
     Admit
    0.44
     อื่น
    0.43
    สำหรับ
    0.42
     Questionnaire
    0.42
     procédés
    0.42
     Customer
    0.42
     Reconstruction
    0.42
    Activations Density 0.000%

    No Known Activations