© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81488
    Prev
    Next
    INDEX
    Explanations

    mathematical functions including exponential and log

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

    The neuron fires on numeric values, mathematical symbols, and formula‐like fragments (i.e. digits, operators, and related technical tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     minOccurs
    -0.86
    pmatrix
    -0.82
    senha
    -0.82
    ruh
    -0.82
    cinct
    -0.80
     itertools
    -0.77
     ورزشی
    -0.77
     berkata
    -0.75
    detto
    -0.75
     Reiter
    -0.74
    POSITIVE LOGITS
     exponential
    1.85
     logarithmic
    1.58
     Log
    1.47
     logistic
    1.43
     log
    1.40
     sigmoid
    1.39
     power
    1.38
     sig
    1.27
    Exponential
    1.26
    log
    1.24
    Activations Density 0.060%

    No Known Activations