© 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. 509
    Prev
    Next
    INDEX
    Explanations

    predicting the next word

    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
    者を
    0.87
    ヤー
    0.83
    継
    0.77
    แส
    0.76
    倆
    0.75
     вто
    0.73
     beleza
    0.70
    力を
    0.70
    erer
    0.69
     свого
    0.69
    POSITIVE LOGITS
     whatnot
    1.53
    decimal
    1.51
     insanely
    1.46
    hourly
    1.41
    weird
    1.41
    initialized
    1.38
    <unused269>
    1.37
    ႅ
    1.37
    <unused925>
    1.36
     weird
    1.36
    Activations Density 0.002%

    No Known Activations