© 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. 10-GEMMASCOPE-RES-131K
    4. 11739
    Prev
    Next
    INDEX
    Explanations

    intelligence test scores

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

    The neuron activates on numeric tokens (e.g. test scores, percentages, measurements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    گوشی
    -1.43
     її
    -1.34
    }\
    -1.30
     și
    -1.27
    还不错
    -1.23
    larda
    -1.13
     їх
    -1.13
    کیف
    -1.13
     sidor
    -1.12
     humaine
    -1.10
    POSITIVE LOGITS
    𝗴
    1.44
     häufigsten
    1.36
    要知道
    1.30
     enfrentan
    1.22
     envió
    1.16
    чне
    1.16
     vermutlich
    1.12
    цуз
    1.10
     gesagt
    1.09
     często
    1.09
    Activations Density 0.039%

    No Known Activations