© 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. 15428
    Prev
    Next
    INDEX
    Explanations

    generate

    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
    คนิค
    0.54
    肯
    0.54
    リート
    0.49
    ović
    0.46
    吏
    0.45
     UnwrapRef
    0.45
    მარ
    0.44
    icuously
    0.44
    
    0.44
    ケン
    0.44
    POSITIVE LOGITS
     generated
    5.03
    生成
    5.03
     generating
    5.00
     generate
    4.97
    generate
    4.88
     generation
    4.78
     Generate
    4.78
     Generating
    4.78
    Generate
    4.69
    generating
    4.69
    Activations Density 0.192%

    No Known Activations