© 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. 58696
    Prev
    Next
    INDEX
    Explanations

    logging in code

    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
     घिरा
    0.42
    tom
    0.39
     فون
    0.39
    ப்புகளில்
    0.38
     만들어
    0.38
     Ху
    0.37
    cohols
    0.37
    蔻
    0.37
    aban
    0.36
    èce
    0.36
    POSITIVE LOGITS
     сервис
    0.42
     Advancement
    0.41
    हार
    0.40
     precarious
    0.40
    爪
    0.40
     advancement
    0.39
    এন
    0.38
     profess
    0.38
    рение
    0.38
    ər
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.