© 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. 247098
    Prev
    Next
    INDEX
    Explanations

    account, period, book, course, free, invested

    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
    ("--
    0.47
     regeneration
    0.47
    ಾ
    0.46
    Writable
    0.46
    まとめ
    0.45
    ాం
    0.45
    깡
    0.44
     מו
    0.44
     લી
    0.42
    Airbnb
    0.42
    POSITIVE LOGITS
     Firma
    0.53
     leur
    0.50
     Their
    0.48
     their
    0.47
     firma
    0.46
     jų
    0.46
     Farrell
    0.45
     leurs
    0.44
     fondo
    0.43
    他们的
    0.43
    Activations Density 0.002%

    No Known Activations