© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1288
    Prev
    Next
    INDEX
    Explanations

    greater than operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     ‍
    0.82
    ‍
    0.80
    덜
    0.69
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.69
     హైద
    0.63
    !!"
    0.61
    ِّ
    0.60
    !!!!
    0.59
    emoration
    0.59
     Mildred
    0.57
    POSITIVE LOGITS
    >
    4.89
     >
    4.82
    >,
    4.36
    ＞
    4.31
    >.
    4.29
    >>
    4.21
    >(
    4.14
    >"
    3.97
    >\
    3.96
    >:
    3.95
    Activations Density 0.398%

    No Known Activations