© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1399
    Prev
    Next
    INDEX
    Explanations

    built into

    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
     &
    0.83
     “
    0.82
    /
    0.80
     sustainable
    0.73
     forthcoming
    0.71
     an
    0.71
     end
    0.70
     fundamental
    0.70
     departe
    0.69
     modern
    0.68
    POSITIVE LOGITS
     初始化
    1.43
    初始化
    1.42
    ByUser
    1.41
    防止
    1.37
    ቮ
    1.33
     이동
    1.31
    Initializing
    1.30
    രാണ്
    1.29
    collisions
    1.29
    ಗಳಿಂದ
    1.29
    Activations Density 0.000%

    No Known Activations