© 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. 206977
    Prev
    Next
    INDEX
    Explanations

    arrangements, directors, War

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

    avoiding vulnerability, requiring things, potential

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ;&#
    0.56
     kän
    0.50
     महंगे
    0.49
     हेव
    0.48
     буд
    0.48
     कोटा
    0.47
    龊
    0.47
    தம்
    0.47
     Selling
    0.47
    ถนน
    0.46
    POSITIVE LOGITS
     inhalation
    0.42
     पसर
    0.41
     واقعات
    0.41
    Fact
    0.40
    slam
    0.39
    ons
    0.39
     Verbre
    0.39
    ˙
    0.38
    发生的
    0.38
    Propagation
    0.38
    Activations Density 0.000%

    No Known Activations