© 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. 166055
    Prev
    Next
    INDEX
    Explanations

    verbing + connective

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

    brief meeting

    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
    毌
    0.47
    ネイ
    0.46
    嘏
    0.43
    鍏
    0.43
    Dou
    0.43
    马克
    0.43
    辄
    0.42
    笳
    0.42
    ๚
    0.42
     pís
    0.42
    POSITIVE LOGITS
     uso
    0.42
     competitivo
    0.41
     edible
    0.41
    opio
    0.41
     उत्पा
    0.40
     pendapat
    0.40
     filename
    0.40
    ৃতা
    0.40
     progreso
    0.40
     आजमा
    0.40
    Activations Density 0.000%

    No Known Activations