© 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. 87933
    Prev
    Next
    INDEX
    Explanations

    smoking, updates, Dalai Lama, autism

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

    expected to / joint / penalty

    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
    作物
    0.46
     Contracting
    0.45
    吉
    0.45
    学校
    0.45
    काने
    0.44
    操作
    0.44
    ಪಾ
    0.44
     UserManager
    0.44
    埥
    0.43
     σημα
    0.42
    POSITIVE LOGITS
     tira
    0.57
    goes
    0.57
     poema
    0.54
     governo
    0.53
     knows
    0.53
    is
    0.50
     tahu
    0.49
     moderno
    0.49
    know
    0.49
     temu
    0.49
    Activations Density 0.000%

    No Known Activations