© 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. 74141
    Prev
    Next
    INDEX
    Explanations

    emphasis, tone, and mannerisms

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

    speech modifiers and intensity

    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
    默默
    0.49
    那么
    0.46
    响应
    0.45
    tìm
    0.43
    泪
    0.42
     Objet
    0.41
    悄
    0.41
    各项
    0.41
    笑了
    0.40
     অজানা
    0.40
    POSITIVE LOGITS
     emphasis
    0.47
     emphasizes
    0.45
     emphasize
    0.45
     uppercase
    0.42
     snail
    0.41
     pronunciation
    0.40
     emphasizing
    0.40
     emph
    0.40
     refers
    0.39
    強調
    0.39
    Activations Density 0.015%

    No Known Activations