© 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. 35712
    Prev
    Next
    INDEX
    Explanations

    code imports and definitions

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

    This neuron fires on digit sequences (numeric literals), highlighting numbers like line counts, IDs, version numbers, 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
    🔑
    -1.23
    🥋
    -1.20
    "…
    -1.13
    💭
    -1.13
     refugi
    -1.07
    🪐
    -1.03
     norvég
    -1.02
    ⌚
    -1.00
     fala
    -1.00
    ♬
    -0.99
    POSITIVE LOGITS
     also
    1.06
    сыз
    1.02
    が出来
    1.00
     będ
    0.98
    更大的
    0.98
     creado
    0.97
     Unterschiede
    0.96
     κάθε
    0.96
     chcia
    0.95
     Änderungen
    0.94
    Activations Density 0.044%

    No Known Activations