© 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. 1704
    Prev
    Next
    INDEX
    Explanations

    finding errors automatically

    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
    1.61
    -
    1.36
    ↵↵
    1.17
    h
    1.17
    ,
    1.11
    /
    1.09
    f
    1.06
    ↵
    1.05
     (
    1.02
    <start_of_image>
    1.02
    POSITIVE LOGITS
    𒌐
    3.07
    𒈫
    3.07
    𒄖
    3.06
    𒆍
    3.04
    𒈤
    3.04
    𒄈
    3.03
    chromiumfx
    3.03
    𒃷
    3.03
    𒌜
    3.01
    𒀠
    3.01
    Activations Density 0.062%

    No Known Activations