© 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. 113174
    Prev
    Next
    INDEX
    Explanations

    preceding punctuation

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

    The neuron activates on standalone numeric tokens (e.g. counts, percentages, version numbers).

    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
     нашего
    -1.25
     we
    -1.24
     Meksiku
    -1.20
    inaudible
    -1.15
     unseres
    -1.13
     apakah
    -1.12
     другие
    -1.11
     they
    -1.10
     prépare
    -1.10
     jusqu
    -1.09
    POSITIVE LOGITS
     all
    1.46
    :
    1.27
    RÉ
    1.21
     a
    1.17
    ļas
    1.06
    xlim
    1.05
    BITDA
    1.02
    setAll
    1.00
    əm
    1.00
     mostly
    1.00
    Activations Density 0.112%

    No Known Activations