© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 419
    Prev
    Next
    INDEX
    Explanations

    tone you're going for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    whatever
    0.82
     whatever
    0.78
    a
    0.77
     whichever
    0.76
     các
    0.75
    i
    0.74
    isten
    0.74
     các
    0.73
     classico
    0.72
    iidae
    0.71
    POSITIVE LOGITS
    徴
    0.77
    ζο
    0.75
    求
    0.73
     搭
    0.73
     好
    0.72
     лов
    0.72
    顺利
    0.71
     बॉय
    0.71
     社会
    0.71
    吓
    0.71
    Activations Density 0.616%

    No Known Activations