© 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. 172097
    Prev
    Next
    INDEX
    Explanations

    table and payment information

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

    generating ideas

    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
    誣
    0.53
    兗
    0.53
     batteria
    0.50
     paziente
    0.49
     arabe
    0.48
     substantiate
    0.48
    ૄ
    0.48
     seduce
    0.47
    必要な
    0.47
     bajos
    0.47
    POSITIVE LOGITS
    ied
    0.54
    ,
    0.54
    era
    0.51
    are
    0.50
    ök
    0.49
    unehmen
    0.49
    ator
    0.47
    utherland
    0.47
    ye
    0.47
    ica
    0.46
    Activations Density 0.000%

    No Known Activations