© 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. 1303
    Prev
    Next
    INDEX
    Explanations

    your placeholder

    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
    которые
    1.46
     التربيع
    1.39
    weise
    1.31
    ة
    1.30
    ๅ
    1.27
    bogen
    1.26
    след
    1.24
    ższy
    1.23
    찢
    1.23
     えっと
    1.22
    POSITIVE LOGITS
    cas
    1.46
    prar
    1.44
    ilia
    1.42
    cedes
    1.40
     {}",
    1.39
    pur
    1.39
     OJ
    1.37
    '
    1.36
    ϡ
    1.35
    posing
    1.32
    Activations Density 0.046%

    No Known Activations