© 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. 99680
    Prev
    Next
    INDEX
    Explanations

    articles and descriptive nouns

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

    The neuron activates on numeric tokens—digits, multi‐digit numbers, and decimal 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
     there
    -1.47
    蘋
    -1.21
    موت
    -1.19
     tevreden
    -1.15
     gebruikt
    -1.14
    LikeLiked
    -1.13
     because
    -1.13
     it
    -1.09
     vergeten
    -1.06
     chrétiens
    -1.05
    POSITIVE LOGITS
     alcune
    1.22
     molte
    1.17
     ordinaria
    1.16
    ienes
    1.14
     ggf
    1.10
    ㎡
    1.09
    breviations
    1.09
     soffer
    1.09
     INFORMACIÓN
    1.09
     edifici
    1.08
    Activations Density 0.075%

    No Known Activations