© 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. 207125
    Prev
    Next
    INDEX
    Explanations

    directions, distances, and food

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

    separating punctuation

    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
     '
    0.53
    ↵↵
    0.50
    使
    0.48
     دارد
    0.48
    更
    0.47
     of
    0.46
    static
    0.46
    在
    0.46
     Dee
    0.46
    0.45
    POSITIVE LOGITS
    hovah
    0.62
    jResponse
    0.57
     ہمارا
    0.53
    ("--
    0.52
     собаки
    0.50
     naše
    0.49
     filets
    0.49
    <unused28>
    0.49
    𝕠
    0.48
     воздействия
    0.48
    Activations Density 0.001%

    No Known Activations