© 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. 153410
    Prev
    Next
    INDEX
    Explanations

    shaped paper

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

    Cheese and fillings

    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
     印
    0.52
     вакан
    0.50
     Eleanor
    0.50
     エン
    0.50
    وری
    0.48
     ulteriori
    0.48
     einzel
    0.48
     Einf
    0.47
     communs
    0.47
    ර්
    0.47
    POSITIVE LOGITS
    埇
    0.48
    math
    0.46
    ⑴
    0.46
    lik
    0.46
    苇
    0.45
    Been
    0.45
    spi
    0.44
    prepared
    0.44
    lia
    0.44
    ricting
    0.44
    Activations Density 0.001%

    No Known Activations