© 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. 39751
    Prev
    Next
    INDEX
    Explanations

    superheroes, modular, driver, county

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

    hypothetical followed by explanation

    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
     ਸਿੰ
    0.54
    builtin
    0.52
    ဖြင့်
    0.50
     ਵਰ
    0.48
    licted
    0.47
    neur
    0.46
    ವಾರು
    0.46
    $/../../
    0.46
    MODE
    0.45
    バス
    0.45
    POSITIVE LOGITS
    ни
    0.53
    רים
    0.52
    imiz
    0.47
    ין
    0.46
     CAB
    0.45
     П
    0.44
     США
    0.44
     Arkadaşlar
    0.43
     PCD
    0.42
     Calvary
    0.42
    Activations Density 0.001%

    No Known Activations