© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14147
    Prev
    Next
    INDEX
    Explanations

    prioritize speed and safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     be
    0.66
    ד
    0.57
     in
    0.57
     an
    0.57
    /
    0.56
    大
    0.55
    প
    0.52
    ;
    0.50
    ด
    0.50
    ח
    0.49
    POSITIVE LOGITS
    า
    0.57
    ാൽ
    0.52
     poise
    0.52
    orer
    0.52
     качество
    0.51
    oure
    0.51
     хуже
    0.50
    उड
    0.50
    時間は
    0.49
    oleh
    0.49
    Activations Density 0.030%

    No Known Activations