© 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. 26346
    Prev
    Next
    INDEX
    Explanations

    offers, himself, statements

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

    This neuron responds to numeric references, i.e. digits or number words (like “third,” “76,” “139,” etc.).

    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
     یا
    -0.91
     пара
    -0.91
    uschen
    -0.87
    ifiquement
    -0.86
     mó
    -0.84
    Either
    -0.84
     representar
    -0.84
     siap
    -0.84
     его
    -0.83
     dû
    -0.82
    POSITIVE LOGITS
     අ
    0.93
     tutela
    0.91
     condominio
    0.88
     confezione
    0.86
    revel
    0.86
    OC
    0.86
     proveniente
    0.84
     doubtnut
    0.84
     sfera
    0.84
     trug
    0.84
    Activations Density 0.052%

    No Known Activations