© 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. 71279
    Prev
    Next
    INDEX
    Explanations

    keeping a journal

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

    can benefit or contribute

    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
     genomes
    0.46
    امہ
    0.43
     wisatawan
    0.43
     urmă
    0.42
    стями
    0.41
     carcinomas
    0.41
    ὔ
    0.41
     deuteron
    0.40
     wisata
    0.40
    اؤ
    0.40
    POSITIVE LOGITS
     الحر
    0.53
    1
    0.52
    pJ
    0.49
     hereof
    0.49
    herr
    0.48
    rs
    0.48
     क्रिया
    0.47
     ಅಗ
    0.47
    ophysical
    0.47
    isher
    0.47
    Activations Density 0.000%

    No Known Activations