© 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. 150508
    Prev
    Next
    INDEX
    Explanations

    permanent exhibition

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

    major storm or incredibly powerful

    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
    <0x80>
    0.49
    চিব
    0.46
    பிலோ
    0.46
    ক্রিয়
    0.46
     culpable
    0.46
    ності
    0.45
    エイ
    0.45
    дьми
    0.45
     ধারণা
    0.44
    Ռ
    0.44
    POSITIVE LOGITS
     stol
    0.47
     association
    0.46
     skl
    0.44
     ढूं
    0.44
    lung
    0.43
     ski
    0.43
    hyd
    0.43
     منص
    0.42
     unbeatable
    0.42
     puk
    0.42
    Activations Density 0.000%

    No Known Activations