© 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. 38647
    Prev
    Next
    INDEX
    Explanations

    further succeeds

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

    energy, attraction, information

    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
     合
    0.45
    gradle
    0.45
    ্বের
    0.44
    ButtonGroup
    0.43
     اخذنا
    0.43
    ри
    0.43
    ट्टा
    0.43
    ੇ
    0.43
    اديه
    0.43
     Балтбет
    0.43
    POSITIVE LOGITS
    สังคม
    0.47
     sociais
    0.46
     sosial
    0.44
    Так
    0.43
     সমাজ
    0.43
     социальной
    0.42
    ລິ
    0.42
     আশ
    0.42
    সমাজ
    0.42
     banned
    0.41
    Activations Density 0.000%

    No Known Activations