© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67571
    Prev
    Next
    INDEX
    Explanations

    numbers and iterators

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

    The neuron responds to numeric tokens or digit sequences (i.e. it spots numbers and indices in the text).

    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
    -
    -1.36
     [
    -1.32
    [
    -1.16
     former
    -1.15
    应该是
    -1.14
    kk
    -1.12
    p
    -1.11
     и
    -1.09
    "…
    -1.09
    kat
    -1.07
    POSITIVE LOGITS
     this
    1.58
     itong
    1.27
    ሸ
    1.19
    احب
    1.18
     claramente
    1.17
    יך
    1.16
    inverno
    1.16
    ))$_
    1.16
    ждении
    1.13
    至此
    1.13
    Activations Density 0.078%

    No Known Activations