© 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. 1569
    Prev
    Next
    INDEX
    Explanations

    dialogue attribution

    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
    читы
    0.71
    喤
    0.70
    相同
    0.69
     yh
    0.68
    при
    0.68
    бра
    0.67
    𝚣
    0.64
    脩
    0.64
     ADMIN
    0.64
     {_
    0.64
    POSITIVE LOGITS
    وكان
    0.87
    Malley
    0.81
     Orchid
    0.78
    ′
    0.78
    
    0.77
    ’
    0.77
    €™
    0.77
    nlü
    0.75
     Bayou
    0.75
    rsquo
    0.73
    Activations Density 0.607%

    No Known Activations