© 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. 3474
    Prev
    Next
    INDEX
    Explanations

    do not or do

    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
    <blockquote>
    2.57
    <h6>
    2.28
    <h3>
    2.27
    이렇게
    2.27
    ūt
    2.26
     কোনো
    2.17
    <h5>
    2.17
    پس
    2.11
    ی
    2.05
    没有
    2.04
    POSITIVE LOGITS
    מצע
    2.04
     Negro
    1.90
    className
    1.83
    storeItem
    1.82
     confeder
    1.77
    ErrorCode
    1.75
     #:
    1.75
     coordinate
    1.75
     INC
    1.74
    ERON
    1.71
    Activations Density 0.333%

    No Known Activations