© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27194
    Prev
    Next
    INDEX
    Explanations

    specific factual entities

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

    The neuron fires on numeric expressions and quantified measures—numbers, amounts, counts, and units in contexts like money, statistics, or quantities.

    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
    ～～～
    -1.16
     visitare
    -1.13
     =[]
    -1.13
     terlaris
    -1.09
    Fonto
    -1.06
     termurah
    -1.05
     کردی
    -1.05
     getNome
    -1.04
     pemandangan
    -1.03
     не
    -1.00
    POSITIVE LOGITS
     expérimentés
    1.29
     Hinsicht
    1.10
     concernés
    1.09
    μερα
    1.07
     vélo
    1.06
     ferv
    1.06
     printemps
    1.03
     laikā
    1.02
     verletzt
    1.02
     semillas
    1.02
    Activations Density 0.076%

    No Known Activations