© 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. 172051
    Prev
    Next
    INDEX
    Explanations

    . followed by words

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

    potential ideas and blueprints

    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
    ت
    0.51
    \*
    0.50
     Wiss
    0.50
     lanc
    0.48
    NORTH
    0.48
    ิ
    0.47
    Otros
    0.47
    س
    0.47
    Not
    0.46
    ELLOW
    0.46
    POSITIVE LOGITS
    igde
    0.45
    从未
    0.45
    úan
    0.44
    omely
    0.44
    refreshToken
    0.43
    ü
    0.43
    üşt
    0.42
    ្ល
    0.42
     इंत
    0.42
    uator
    0.41
    Activations Density 0.000%

    No Known Activations