© 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. 106428
    Prev
    Next
    INDEX
    Explanations

    names, places, or concepts

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

    how components function

    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
     ...");
    0.56
     timeCounter
    0.53
    """,
    0.49
     ausgestattet
    0.49
     égale
    0.49
     جميعا
    0.48
    aloko
    0.47
     TNumber
    0.47
    er
    0.46
     النموذج
    0.46
    POSITIVE LOGITS
     compliments
    0.52
     abuses
    0.46
     portals
    0.44
    数
    0.44
     High
    0.42
     criteria
    0.42
     patios
    0.41
    気に入り
    0.41
     relev
    0.41
     cottages
    0.41
    Activations Density 0.000%

    No Known Activations