© 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. 53155
    Prev
    Next
    INDEX
    Explanations

    programming code context

    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
    お
    0.46
     refundable
    0.43
     finans
    0.40
     बैंकों
    0.40
     preferentially
    0.39
     intersect
    0.39
     unf
    0.39
    合作
    0.39
     financieros
    0.39
     preferential
    0.38
    POSITIVE LOGITS
     своего
    0.42
    ühlt
    0.42
    Neill
    0.41
    }^{*}(\
    0.40
    惶
    0.40
    漂亮
    0.39
     بود
    0.39
     arrête
    0.39
     Assuming
    0.39
     காட்ச
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.