© 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. 130246
    Prev
    Next
    INDEX
    Explanations

    marathonaccommodationsshown

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

    jigsaw

    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
    Z
    0.52
    to
    0.48
    F
    0.47
    Q
    0.46
    S
    0.46
    і
    0.44
    V
    0.44
    ec
    0.44
    7
    0.42
    《
    0.42
    POSITIVE LOGITS
    庿
    0.54
     سیاست
    0.50
     cálculos
    0.47
     menú
    0.47
     بیم
    0.46
     explicación
    0.46
     দ্বারা
    0.46
    ítás
    0.45
     sculptural
    0.45
     superbe
    0.45
    Activations Density 0.001%

    No Known Activations