© 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. 240334
    Prev
    Next
    INDEX
    Explanations

    Wilfrid, Supreme Court, news/

    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
    蛔
    0.47
     आफ्टर
    0.47
    '।
    0.46
    }$:
    0.45
    seq
    0.45
    rror
    0.44
     فى
    0.44
     ৪৮
    0.44
    ణ్
    0.44
    стина
    0.43
    POSITIVE LOGITS
     areas
    0.66
     paradise
    0.54
     bands
    0.53
     crews
    0.53
     errands
    0.52
    ר
    0.51
     zones
    0.50
     angina
    0.50
     wonderland
    0.49
     garages
    0.49
    Activations Density 0.000%

    No Known Activations