© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 109328
    Prev
    Next
    INDEX
    Explanations

    vocal cords, folds, and technique

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    political
    0.63
    Political
    0.57
     political
    0.53
    husband
    0.51
    瑰
    0.47
    valuate
    0.47
    :+
    0.46
    voices
    0.46
    arrest
    0.46
    personality
    0.46
    POSITIVE LOGITS
    చ్చే
    0.56
    테
    0.55
     şeyler
    0.55
     Alberts
    0.55
     Vit
    0.54
     algumas
    0.53
     Albert
    0.52
     vitaminas
    0.52
     empecé
    0.52
     alcune
    0.51
    Activations Density 0.005%

    No Known Activations