© 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. 98247
    Prev
    Next
    INDEX
    Explanations

    introduces features or specifics

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

    consider or focus on specific aspects

    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
     자연
    0.47
    गेशन
    0.44
     เห็น
    0.42
     гало
    0.42
     전쟁
    0.41
     범
    0.41
     꺼
    0.40
    可以让
    0.40
     увеличи
    0.40
     숫자
    0.40
    POSITIVE LOGITS
     diagnóstico
    0.44
     a
    0.44
     SPARSE
    0.44
     symptômes
    0.43
     Wrestling
    0.42
    EDGE
    0.42
     intermitt
    0.41
    SMTP
    0.41
    PE
    0.40
     conhecimento
    0.40
    Activations Density 0.000%

    No Known Activations