© 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. 22-GEMMASCOPE-RES-131K
    7. 72602
    Prev
    Next
    INDEX
    Explanations

    specific foreign words

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

    This neuron fires on structured‐document tokens that are either numbers or uppercase identifiers/labels (e.g. numeric IDs, XML tag names, or all-caps acronyms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     énorm
    -1.20
    Dijo
    -1.17
    肿
    -1.14
     Tienen
    -1.13
     oeil
    -1.10
     samoz
    -1.09
     путем
    -1.05
    dolphin
    -1.05
     we
    -1.04
    ייה
    -1.04
    POSITIVE LOGITS
     бампер
    1.29
     calificación
    1.27
    typeorm
    1.27
     finalidad
    1.25
    område
    1.23
     Hochschule
    1.21
     or
    1.20
     пароль
    1.20
     pantalón
    1.19
    æring
    1.17
    Activations Density 0.011%

    No Known Activations