© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11814
    Prev
    Next
    INDEX
    Explanations

    logarithm functions

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

    The neuron fires on occurrences of “log” or “logarithm” (and related numeric logarithmic terms) in equations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     defocused
    0.85
     equivariant
    0.82
    ^{-
    0.79
     birefring
    0.79
     defocus
    0.78
     suppressing
    0.76
     nonzero
    0.75
     spurious
    0.75
     subtracting
    0.74
     sagittal
    0.72
    POSITIVE LOGITS
    成長
    0.82
     Steam
    0.75
    steam
    0.75
     احت
    0.72
    ladies
    0.71
    GROW
    0.71
    霧
    0.70
     Endowment
    0.69
    ribusiness
    0.68
    țile
    0.68
    Activations Density 0.001%

    No Known Activations