© 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. 198554
    Prev
    Next
    INDEX
    Explanations

    location/field

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

    scams, legal, and responsibly

    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
     pep
    0.52
     its
    0.49
     first
    0.49
     Its
    0.49
     half
    0.48
    ).
    0.46
    );
    0.45
    .)
    0.45
    )&
    0.45
    ]=
    0.44
    POSITIVE LOGITS
    ૄ
    0.53
     представи
    0.51
    荭
    0.51
    Realm
    0.49
    逖
    0.48
     tématu
    0.47
     дат
    0.47
     ferramentas
    0.46
    庥
    0.46
     зараз
    0.46
    Activations Density 0.001%

    No Known Activations