© 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. 7548
    Prev
    Next
    INDEX
    Explanations

    power and exponent

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

    x to the power of

    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
     थाना
    0.47
     காணலாம்
    0.46
     يمكن
    0.46
     สามารถ
    0.46
    freund
    0.45
    ක
    0.43
    diff
    0.43
     இதே
    0.43
    ದಾರ
    0.43
    親
    0.42
    POSITIVE LOGITS
     because
    0.50
     −
    0.46
     因為
    0.44
     anymore
    0.44
     –
    0.42
     minus
    0.41
     powering
    0.41
     porque
    0.40
     ->
    0.40
     +\
    0.39
    Activations Density 0.000%

    No Known Activations