© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3878
    Prev
    Next
    INDEX
    Explanations

    words starting with dis

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

    negative prefix dis

    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_53_width_65k_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
    चौ
    0.40
    淖
    0.39
     Defensive
    0.38
    洸
    0.38
    ይል
    0.37
    轳
    0.37
     incompatible
    0.35
     فع
    0.34
    讖
    0.34
     términos
    0.34
    POSITIVE LOGITS
    ciplinary
    0.76
    ciples
    0.72
    astrous
    0.70
    cretion
    0.70
    claimer
    0.70
    cipline
    0.69
    proportion
    0.67
    gruntled
    0.67
    rupted
    0.65
    appoint
    0.64
    Activations Density 0.036%

    No Known Activations