© 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. 82778
    Prev
    Next
    INDEX
    Explanations

    water heating, subscribe

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

    high-end art prints

    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
     ક્ષ
    0.53
     ولم
    0.44
    o
    0.43
    serial
    0.43
     Mathf
    0.42
     Math
    0.42
     جهت
    0.42
    textArea
    0.41
    flowLayoutPanel
    0.41
     දි
    0.41
    POSITIVE LOGITS
    ेड
    0.58
    িলম্বে
    0.54
    Мне
    0.52
     altern
    0.51
    لاس
    0.51
     bebas
    0.50
    Чем
    0.50
    Н
    0.49
    гато
    0.48
    På
    0.48
    Activations Density 0.000%

    No Known Activations