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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13749
    Prev
    Next
    INDEX
    Explanations

    aesthetic styles

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
     progeny
    0.73
     “
    0.71
    ”!
    0.67
     assemblages
    0.62
     (“
    0.61
    ’!
    0.61
     ″
    0.60
     precludes
    0.59
     disseminating
    0.58
     “.
    0.57
    POSITIVE LOGITS
     Taehyung
    0.82
     simpel
    0.81
     idk
    0.77
     Jungkook
    0.76
    됬
    0.75
     довольно
    0.71
     акку
    0.71
     少し
    0.71
    🛹
    0.70
     Jimin
    0.70
    Activations Density 0.022%

    No Known Activations