© 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. 201281
    Prev
    Next
    INDEX
    Explanations

    routine, horses, anybody, out, devastated, burned

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

    foreign language words

    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
     synd
    0.46
     exacte
    0.45
    :
    0.44
    ♪
    0.43
     described
    0.43
     dissect
    0.43
     dou
    0.42
    >>
    0.42
     les
    0.42
     logique
    0.42
    POSITIVE LOGITS
     ກຳ
    0.55
    ເພ
    0.49
     офис
    0.49
     उपहार
    0.48
     ০৯
    0.48
     नाश
    0.47
     बचे
    0.47
    ంతరం
    0.47
     نبدا
    0.46
     बटन
    0.46
    Activations Density 0.001%

    No Known Activations