© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8454
    Prev
    Next
    INDEX
    Explanations

    mathematical division and operations

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical operations and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     भ्रष्टाचार
    0.60
     Vereinig
    0.57
     demokrat
    0.56
     Democr
    0.55
     谢
    0.55
     Nationale
    0.54
    带领
    0.54
    恽
    0.54
     Politik
    0.54
     instytuc
    0.54
    POSITIVE LOGITS
    +
    0.93
    .
    0.77
     =
    0.76
    =
    0.76
     ×
    0.72
    %
    0.66
     ∈
    0.65
     +
    0.64
    を
    0.64
     ==
    0.64
    Activations Density 0.031%

    No Known Activations