© 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. 109035
    Prev
    Next
    INDEX
    Explanations

    automatically entail

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

    computational complexity and energy alternatives

    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
     आल्स
    0.49
    Ftp
    0.47
    谋
    0.47
     nación
    0.46
     lương
    0.46
     Stacey
    0.45
    FTP
    0.45
    是什么
    0.44
     زمانی
    0.44
    谁
    0.44
    POSITIVE LOGITS
    inputs
    0.40
    ="...">
    0.40
    ма
    0.40
    ਵਾ
    0.40
    ’
    0.40
    グ
    0.39
    творе
    0.39
    ก
    0.39
    ביר
    0.38
    punch
    0.37
    Activations Density 0.000%

    No Known Activations