© 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. 10-GEMMASCOPE-RES-131K
    7. 124716
    Prev
    Next
    INDEX
    Explanations

    through or to

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

    The neuron activates on numeric tokens (e.g. integer or decimal values), i.e. it finds numbers and measurements 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
     одной
    -2.08
     haciendo
    -1.93
     viendo
    -1.88
    According
    -1.88
    Our
    -1.88
     poniendo
    -1.80
     такой
    -1.78
    Since
    -1.75
     has
    -1.75
    When
    -1.74
    POSITIVE LOGITS
    歃
    2.67
    '
    2.39
    髡
    2.25
    蚰
    2.14
     astu
    2.14
     refugi
    2.14
     algod
    2.11
     estruct
    2.08
     frança
    2.06
    潆
    2.06
    Activations Density 0.017%

    No Known Activations