© 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. 107182
    Prev
    Next
    INDEX
    Explanations

    actions and plurals

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

    explains personality traits

    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
     കൃ
    0.45
    たり
    0.45
     (
    0.45
     ${
    0.44
     waisted
    0.43
     Faisal
    0.42
     و
    0.41
    ና
    0.40
     maid
    0.40
    بت
    0.39
    POSITIVE LOGITS
     இதையடுத்து
    0.52
    VERBOSE
    0.49
    🚧
    0.48
    फोर्स
    0.48
     activos
    0.48
    이스
    0.48
     تبدی
    0.47
     kişilik
    0.47
     TESTS
    0.47
     actualmente
    0.46
    Activations Density 0.002%

    No Known Activations