© 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. 8712
    Prev
    Next
    INDEX
    Explanations

    nodded, smiled, or sighed

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

    dialogue attribution for characters

    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
     seasonality
    0.43
    镙
    0.43
    我們會
    0.41
    缟
    0.40
    銨
    0.39
    сійскай
    0.39
    啮
    0.38
     våra
    0.38
    矵
    0.38
    硖
    0.38
    POSITIVE LOGITS
     glanced
    0.50
     hesitated
    0.47
     murmured
    0.46
     nodded
    0.46
    笑道
    0.44
     Xiao
    0.43
     muttered
    0.43
     speechless
    0.43
     smiled
    0.42
     sighed
    0.42
    Activations Density 0.021%

    No Known Activations