© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2640
    Prev
    Next
    INDEX
    Explanations

    multiplication and equality

    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
    cdot
    1.11
    longrightarrow
    1.08
    squre
    0.99
    rightarrow
    0.98
    ❑
    0.95
    sqrt
    0.95
    ====
    0.93
    Rightarrow
    0.93
    ^(
    0.93
    radian
    0.93
    POSITIVE LOGITS
     [{\
    0.86
     \{\
    0.85
     ({\
    0.81
     gov
    0.79
     J
    0.74
     W
    0.73
     [\
    0.73
     EPC
    0.72
     {\
    0.71
     Supp
    0.71
    Activations Density 0.003%

    No Known Activations