© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79774
    Prev
    Next
    INDEX
    Explanations

    code snippets and diverse languages

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

    The neuron fires on standalone numeric literals (multi‐digit numbers) in code or text.

    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
    Gruss
    -1.37
     heilige
    -1.34
     familien
    -1.30
     harten
    -1.27
    Ventajas
    -1.26
    𓃵
    -1.25
    Kelebihan
    -1.20
     Heilige
    -1.19
    Consejos
    -1.18
     träd
    -1.18
    POSITIVE LOGITS
     lichaam
    1.23
    outWeight
    1.23
    tagHelper
    1.22
    ウチ
    1.21
    PreferredItem
    1.21
     vuestro
    1.20
    apura
    1.16
    女人的
    1.13
     Surve
    1.13
    TagHelpers
    1.13
    Activations Density 0.006%

    No Known Activations