© 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. 186891
    Prev
    Next
    INDEX
    Explanations

    suited for

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

    LEGO bricks or blocks

    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
    .
    0.52
    ).
    0.47
    િક
    0.45
     carelessly
    0.44
    ;
    0.44
    ٹ
    0.43
    ě
    0.42
    Y
    0.41
    ή
    0.41
     I
    0.41
    POSITIVE LOGITS
     വ്യത്യ
    0.54
     Versorgung
    0.52
    arquia
    0.52
    Gioco
    0.51
    逭
    0.51
    هام
    0.50
    ឡិចត្រូ
    0.50
    zentrum
    0.49
    dimensioni
    0.49
    專家
    0.48
    Activations Density 0.000%

    No Known Activations