© 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. 120565
    Prev
    Next
    INDEX
    Explanations

    refund questions

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

    visual output or graphical display

    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
     bekannt
    0.44
    有無
    0.43
    荤
    0.43
    ramos
    0.43
    Editar
    0.42
     الخميس
    0.42
     trợ
    0.42
     Aplic
    0.42
    Га
    0.41
     অস্বীকার
    0.41
    POSITIVE LOGITS
    proba
    0.52
    would
    0.48
    or
    0.46
    andex
    0.45
     এসেছিল
    0.45
    etop
    0.44
     periodontal
    0.44
    ¸
    0.44
     worried
    0.44
     IMMEDI
    0.43
    Activations Density 0.002%

    No Known Activations