© 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. 237087
    Prev
    Next
    INDEX
    Explanations

    legal matter

    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
    Б
    0.50
    Т
    0.45
    സില്‍
    0.45
    л
    0.44
    ン
    0.44
     некоторые
    0.43
    に近い
    0.42
    ل
    0.42
    ತ್
    0.42
     अनुपात
    0.42
    POSITIVE LOGITS
    onics
    0.57
     Rock
    0.50
    ppelin
    0.49
     Sole
    0.47
     Kidd
    0.47
    ulent
    0.46
     Lern
    0.46
     Olympics
    0.46
    odigd
    0.46
     Trol
    0.46
    Activations Density 0.000%

    No Known Activations