© 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. 35391
    Prev
    Next
    INDEX
    Explanations

    introduction and blog posts

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

    This neuron selectively activates on numeric tokens and figure‐related terms, effectively detecting where the text is reporting numbers (years, model numbers, statistics, measurements, 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
     my
    -1.66
     people
    -1.52
     any
    -1.47
     when
    -1.45
     great
    -1.27
    People
    -1.26
     get
    -1.22
     our
    -1.21
     every
    -1.20
     one
    -1.20
    POSITIVE LOGITS
     comentar
    1.35
     vetores
    1.34
     todays
    1.30
     célè
    1.27
    dfunding
    1.26
     redacción
    1.24
     explicación
    1.23
     Nguyễn
    1.23
     relojes
    1.20
     autocollant
    1.20
    Activations Density 0.096%

    No Known Activations