© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 86792
    Prev
    Next
    INDEX
    Explanations

    algebraic expressions

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

    This neuron fires on tokens from mathematical equations—Greek-letter function names (like φ), parentheses, equals signs, variables, numbers, and operators—i.e. on formula syntax.

    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
    ”،
    -1.18
    どうやら
    -1.07
    Джерела
    -1.05
     إليها
    -1.03
    Varför
    -1.02
    ṩ
    -1.02
    اقرأ
    -1.02
     geweldige
    -1.01
    ਖ਼
    -0.99
    <em>
    -0.98
    POSITIVE LOGITS
     ->
    1.09
     ...)
    1.07
    ...]
    1.05
     ..
    1.02
     ....
    1.00
    ...)
    0.98
     -->
    0.98
    ...,
    0.96
     [
    0.96
    ..."
    0.94
    Activations Density 0.202%

    No Known Activations