© 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. 94205
    Prev
    Next
    INDEX
    Explanations

    USA, tests, immediately

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

    with caveats

    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
    áveis
    0.46
     magnis
    0.46
    .');
    0.45
    ٹا
    0.45
     endeavours
    0.45
    érieurs
    0.44
     expend
    0.44
    женер
    0.44
    弇
    0.44
    świę
    0.44
    POSITIVE LOGITS
     주민
    0.47
    token
    0.46
     tồn
    0.45
    string
    0.45
    arr
    0.45
    OK
    0.45
    Chosen
    0.44
    group
    0.43
    UN
    0.43
    E
    0.43
    Activations Density 0.003%

    No Known Activations