© 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. 169203
    Prev
    Next
    INDEX
    Explanations

    media director

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

    direct eye contact

    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
     Học
    0.53
    ёшь
    0.49
    ┕
    0.48
     ถ้า
    0.46
    если
    0.46
     recrystall
    0.44
    病院
    0.44
    蘖
    0.44
     brah
    0.44
    ವಿ
    0.43
    POSITIVE LOGITS
     digital
    0.49
     മീഡിയ
    0.49
    ，
    0.46
     deputy
    0.44
     directora
    0.43
    传媒
    0.43
     director
    0.43
     acting
    0.43
     merchandise
    0.42
     الإعلام
    0.42
    Activations Density 0.002%

    No Known Activations