© 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. 40-GEMMASCOPE-2-RES-262K
    7. 168886
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

    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_40_width_262k_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
     casilla
    0.43
    দ্দা
    0.38
     dancer
    0.38
     স্ট্যান্ড
    0.38
    الن
    0.38
    넌
    0.38
    uların
    0.38
    心脏
    0.37
    邓
    0.37
     leb
    0.36
    POSITIVE LOGITS
    EM
    0.42
    Technology
    0.40
    ☢
    0.39
     lag
    0.38
    %),
    0.38
    pads
    0.38
    remove
    0.37
    Lag
    0.37
     প্রযুক্ত
    0.37
     technology
    0.36
    Activations Density 0.001%

    No Known Activations