© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42290
    Prev
    Next
    INDEX
    Explanations

    `[(` and `setopt`

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

    This neuron detects numeric tokens or tokens containing digits (e.g. numbers, numeric literals, or identifiers with digits).

    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
    ↵
    -3.23
     freie
    -2.31
     schnelle
    -2.23
    蜴
    -2.14
    
    -2.09
    祼
    -2.08
     bessere
    -2.05
    besondere
    -2.03
     politische
    -1.96
     locals
    -1.95
    POSITIVE LOGITS
    y
    3.58
    ).
    2.95
     According
    2.44
     However
    2.41
    u
    2.28
    و
    2.27
    replyreport
    2.25
     internationaux
    2.22
     africains
    2.19
     But
    2.14
    Activations Density 0.004%

    No Known Activations