© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1759
    Prev
    Next
    INDEX
    Explanations

    math operations and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sqrt
    0.58
     <
    0.57
     $\{
    0.56
    Arithmetic
    0.55
     $<
    0.54
     <=
    0.53
     >=
    0.52
     sizeof
    0.52
     $=
    0.52
    $`
    0.52
    POSITIVE LOGITS
     idi
    0.46
    実践
    0.43
     reimag
    0.43
     exercitation
    0.43
     memorabilia
    0.42
     gimm
    0.42
     syncing
    0.40
     overhauled
    0.40
    hoon
    0.40
     springing
    0.39
    Activations Density 0.204%

    No Known Activations