© 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. 82841
    Prev
    Next
    INDEX
    Explanations

    society, product, difficult, Nickel, turn, note, week, weather

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

    describes technical or descriptive content

    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
    ня
    0.53
    нина
    0.48
    ORDON
    0.48
    Pot
    0.48
    ampak
    0.47
    IGAN
    0.47
    д
    0.47
    ска
    0.47
    ни
    0.46
    никами
    0.46
    POSITIVE LOGITS
     graphique
    0.52
     Spieler
    0.52
     explique
    0.52
     Curves
    0.52
     பரபர
    0.52
     Numerical
    0.51
     Serious
    0.51
     permettant
    0.51
     ¨
    0.50
     Zentr
    0.50
    Activations Density 0.001%

    No Known Activations