© 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. 6313
    Prev
    Next
    INDEX
    Explanations

    code block endings and errors

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

    closing punctuation

    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
    َة
    0.17
     zariaden
    0.14
    េ
    0.13
     sécrétion
    0.13
    燁
    0.13
    »،
    0.13
    數據
    0.13
     ميل
    0.13
     fistule
    0.13
     diarrh
    0.13
    POSITIVE LOGITS
    ↵
    0.16
     in
    0.14
    <0x0D>
    0.14
     The
    0.13
     In
    0.13
    auto
    0.13
    and
    0.12
     it
    0.12
     On
    0.12
    -
    0.12
    Activations Density 0.001%

    No Known Activations