© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113896
    Prev
    Next
    INDEX
    Explanations

    achieved and knowledgeable

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

    convenient, most, length

    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
    Negative Logits
    সি
    0.53
    Beim
    0.52
    CONCLUS
    0.50
    座標
    0.50
    踰
    0.50
    筞
    0.49
     grudnia
    0.49
    Ό
    0.49
    ěst
    0.48
    Η
    0.48
    POSITIVE LOGITS
    t
    0.54
     p
    0.52
     bull
    0.50
     \
    0.50
     t
    0.49
     very
    0.48
     (
    0.48
     din
    0.47
     tuv
    0.47
    networking
    0.47
    Activations Density 0.003%

    No Known Activations