© 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. 771
    Prev
    Next
    INDEX
    Explanations

    numbers in urls

    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
    ≣
    1.73
    Emoji
    1.70
     dikdört
    1.68
     최대
    1.66
    okatokat
    1.64
     반지름
    1.62
     버전
    1.61
    𐰰
    1.61
    Aslamualaikum
    1.61
    Qaeda
    1.60
    POSITIVE LOGITS
    .
    0.89
    .\"
    0.89
    nes
    0.86
     civil
    0.84
     there
    0.81
    ."
    0.81
    cat
    0.79
    .\
    0.79
     a
    0.79
    ↵↵
    0.79
    Activations Density 0.024%

    No Known Activations