© 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. 199720
    Prev
    Next
    INDEX
    Explanations

    common grammatical pairings

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

    submissive or supervised

    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
    น
    0.59
     चव्हाण
    0.52
    ﺟ
    0.50
    がありました
    0.48
    н
    0.48
    சன்
    0.47
     jeweler
    0.47
    बाब
    0.47
     maker
    0.46
    鄭
    0.46
    POSITIVE LOGITS
     Epid
    0.46
     trabalhando
    0.46
     Rotation
    0.44
     કામ
    0.44
    rs
    0.43
    iego
    0.43
     Requests
    0.43
     Function
    0.43
     epid
    0.43
     Working
    0.43
    Activations Density 0.000%

    No Known Activations