© 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. 161822
    Prev
    Next
    INDEX
    Explanations

    there are / freedom of

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

    what to say about roots and culture

    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
    透明
    0.46
     வெறும்
    0.46
    equivariant
    0.45
    ^{*}(
    0.44
    transparent
    0.43
    វេ
    0.43
    ﾓ
    0.43
     पिंड
    0.42
    ﾋ
    0.42
    entire
    0.42
    POSITIVE LOGITS
    ستی
    0.52
     monastery
    0.47
    ز
    0.47
    س
    0.45
    رب
    0.45
     rodzaju
    0.45
     berätt
    0.45
     Biotechnology
    0.45
     sağlay
    0.45
     Salaries
    0.44
    Activations Density 0.000%

    No Known Activations