© 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. 11240
    Prev
    Next
    INDEX
    Explanations

    python code with numpy

    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
    un
    1.77
    ar
    1.76
    ie
    1.62
     trữ
    1.58
    unk
    1.58
    先
    1.54
    il
    1.47
    is
    1.47
    灌
    1.47
     knih
    1.43
    POSITIVE LOGITS
    ючись
    2.23
    eah
    2.11
     Sinn
    2.10
    <unused2162>
    2.08
    <unused172>
    2.07
    eaa
    2.06
    <unused2206>
    2.05
    𒀭
    2.00
     Beasley
    1.99
    <unused400>
    1.99
    Activations Density 0.000%

    No Known Activations