© 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. 30602
    Prev
    Next
    INDEX
    Explanations

    upwards and from

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

    person may be classified

    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
    </strong>
    0.51
     cytoplasm
    0.48
    (
    0.47
     palind
    0.46
    }
    0.46
     axes
    0.45
    /
    0.44
     switch
    0.44
     plasmid
    0.44
    0
    0.44
    POSITIVE LOGITS
     আন্তরিক
    0.55
    धिकारिक
    0.51
     altın
    0.50
    了很多
    0.48
    बारक
    0.48
    ্বল
    0.47
    ьогодні
    0.47
     بسیاری
    0.47
    <unused80>
    0.46
     खूब
    0.46
    Activations Density 0.000%

    No Known Activations