© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11293
    Prev
    Next
    INDEX
    Explanations

    SageMaker, SageMath

    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_7_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
    iony
    2.21
     Supp
    2.04
    ě
    1.98
    islav
    1.95
    iling
    1.95
    rasz
    1.93
    ække
    1.93
    onicus
    1.88
    ătate
    1.79
    мови
    1.79
    POSITIVE LOGITS
    𝘬
    2.77
    𝘈
    2.68
    𝘰
    2.62
    𝘖
    2.48
    сибир
    2.45
    𝘞
    2.43
    𝘐
    2.37
    initions
    2.35
    VCTargetsPath
    2.35
    𝘯
    2.32
    Activations Density 0.001%

    No Known Activations