© 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. 244265
    Prev
    Next
    INDEX
    Explanations

    specific categories and attributes

    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
     मलिक
    0.51
    Дата
    0.46
     boobs
    0.46
    傌
    0.46
    гистра
    0.46
     ম্যা
    0.44
     לא
    0.44
     پیغام
    0.44
    MessageNow
    0.43
    ኪ
    0.43
    POSITIVE LOGITS
     對
    0.45
     justifying
    0.44
    whose
    0.43
     simplification
    0.43
     Substitution
    0.43
     defensive
    0.43
     substitution
    0.43
     sogenannten
    0.43
    〔
    0.43
    ವಿಧ
    0.43
    Activations Density 0.001%

    No Known Activations