© 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. 108722
    Prev
    Next
    INDEX
    Explanations

    sorted and arranged items

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

    categorize members

    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
    שו
    0.44
     européenne
    0.44
    または
    0.42
    ﾗ
    0.42
     machinist
    0.41
     vscode
    0.41
    ssh
    0.40
    Milliseconds
    0.40
     nebo
    0.40
    ర్‌
    0.39
    POSITIVE LOGITS
     इम्यून
    0.47
     oddly
    0.47
     popped
    0.47
     hyped
    0.46
    卄
    0.45
     इतर
    0.45
     букмекеры
    0.44
     arranged
    0.43
     abnormally
    0.43
     smelled
    0.42
    Activations Density 0.000%

    No Known Activations