© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12497
    Prev
    Next
    INDEX
    Explanations

    Jim Crow Laws

    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
     '*')
    2.97
    𝑙
    2.92
    𝑟
    2.74
    ('$(
    2.57
    𝑓
    2.55
    𝑣
    2.52
    icc
    2.43
    થમ
    2.43
    ות
    2.42
    🏵
    2.36
    POSITIVE LOGITS
    گران
    2.89
    フォード
    2.66
    anigans
    2.61
    ca
    2.51
     stort
    2.48
    %"
    2.42
     Dump
    2.41
    crates
    2.40
    erca
    2.39
    megaphone
    2.39
    Activations Density 0.013%

    No Known Activations