© 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. 68426
    Prev
    Next
    INDEX
    Explanations

    contrasting pairs or sequences

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

    The neuron activates on numerical tokens—digits or number-like substrings in the 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
    xr
    -0.86
    Geographie
    -0.85
     part
    -0.82
    bott
    -0.81
     cabelo
    -0.81
    dată
    -0.81
     homens
    -0.79
    iramente
    -0.79
    ualmente
    -0.79
    ungszeit
    -0.79
    POSITIVE LOGITS
     paramInt
    0.85
    hadapi
    0.81
    哈哈哈
    0.75
    Fakta
    0.75
    parseDouble
    0.73
    CaseSensitive
    0.73
    決勝
    0.73
     shepherd
    0.73
    Teknik
    0.73
    用于
    0.71
    Activations Density 0.126%

    No Known Activations