© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6523
    Prev
    Next
    INDEX
    Explanations

    if you or applicable

    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_16k_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
    ники
    2.42
    挲
    2.41
    𝐭
    2.39
     guiclass
    2.33
     учу
    2.25
    lections
    2.12
    𝐯
    2.12
    новой
    2.10
    onson
    2.10
    𝐫
    2.08
    POSITIVE LOGITS
    м
    2.88
    에
    2.87
    ו
    2.64
    고
    2.39
    i
    2.34
    en
    2.26
    că
    2.11
    onaut
    2.09
    စဉ်
    2.09
    pain
    2.08
    Activations Density 0.074%

    No Known Activations