© 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. 249519
    Prev
    Next
    INDEX
    Explanations

    buying or selling

    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
    🍜
    0.55
     आरक्षण
    0.53
     punctatis
    0.53
    ıları
    0.53
     Δεν
    0.53
    轳
    0.52
     cognitiva
    0.52
     प्रमुख
    0.51
    चलर्स
    0.51
     tedav
    0.51
    POSITIVE LOGITS
    t
    0.68
    in
    0.64
    기
    0.60
    n
    0.59
    an
    0.56
    IN
    0.56
    l
    0.55
    INE
    0.52
    元
    0.52
    k
    0.52
    Activations Density 0.001%

    No Known Activations