© 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. 3103
    Prev
    Next
    INDEX
    Explanations

    order management and processing

    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
     createSprite
    2.94
    Fold
    2.80
    PSON
    2.78
    ‍♂
    2.73
     meninos
    2.72
    有人
    2.70
    FirstResponder
    2.62
    娲
    2.62
    vnd
    2.61
     popupButton
    2.60
    POSITIVE LOGITS
    liness
    3.10
    ment
    2.58
    ra
    2.28
    jeta
    2.11
    finden
    2.10
    lo
    2.05
    ungen
    2.03
    도의
    2.02
    ઠવા
    2.02
    aln
    2.01
    Activations Density 0.062%

    No Known Activations