© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 104930
    Prev
    Next
    INDEX
    Explanations

    numbers and specific words

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

    political entities and societal issues

    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
     Sutherland
    0.53
    the
    0.52
    u
    0.52
     General
    0.48
     Metal
    0.48
     “
    0.47
     Raj
    0.47
     the
    0.47
     ej
    0.46
     Telephone
    0.46
    POSITIVE LOGITS
    homeini
    0.61
     inhum
    0.53
     मुसलमानों
    0.52
    ಲೆಂ
    0.51
    kirche
    0.47
    ICPSR
    0.47
     unjustly
    0.47
    娼
    0.47
     musul
    0.46
    وشن
    0.46
    Activations Density 0.001%

    No Known Activations