© 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. 27158
    Prev
    Next
    INDEX
    Explanations

    time, years, all

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

    scenario setting or role-playing prompts

    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
     Gaussian
    0.46
    )^
    0.45
     Για
    0.45
     Γερμαν
    0.44
    ೂರ್ಣ
    0.43
     সমাধান
    0.43
    Έ
    0.43
     과학
    0.43
    мето
    0.43
     Р
    0.43
    POSITIVE LOGITS
     täglich
    0.49
     ежедневно
    0.46
     افواج
    0.46
    នៅក្នុង
    0.45
     sienten
    0.44
     régulièrement
    0.42
    ють
    0.41
    िक्रमा
    0.41
     película
    0.41
    ckenridge
    0.40
    Activations Density 0.000%

    No Known Activations