© 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. 44106
    Prev
    Next
    INDEX
    Explanations

    entity type classifications

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

    This neuron activates on numeric tokens—especially digits and numbers used in code (e.g. migration IDs, version numbers, and similar numeric identifiers).

    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
    痪
    -1.40
     ähnlichen
    -1.25
     liknande
    -1.24
     piemē
    -1.22
     ļ
    -1.20
    日に
    -1.20
    Mittwoch
    -1.20
    任何
    -1.20
     nepiecieš
    -1.18
     līdz
    -1.16
    POSITIVE LOGITS
     at
    1.38
     one
    1.37
     too
    1.34
    Australie
    1.20
     Пока
    1.20
    魄
    1.18
    藹
    1.18
     four
    1.18
    Categorias
    1.16
     intensif
    1.15
    Activations Density 0.023%

    No Known Activations