© 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. 10-GEMMASCOPE-RES-131K
    7. 69894
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

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

    This neuron fires on numeric literals and related tokens (e.g. integers, floating‐point numbers, regex quantifiers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     been
    -1.52
     aggiungere
    -1.41
    انا
    -1.40
     ")[
    -1.35
     piccole
    -1.35
    
    -1.33
     swivel
    -1.30
     potrà
    -1.29
    是被
    -1.27
     constater
    -1.24
    POSITIVE LOGITS
    焄
    1.38
    umbledore
    1.38
    Initially
    1.30
    員の
    1.27
    းက
    1.24
    引用元
    1.23
    rentiel
    1.23
    撺
    1.22
    (≧
    1.20
    ៚
    1.19
    Activations Density 0.004%

    No Known Activations