© 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. 11629
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by descriptive words

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

    The neuron activates on numeric values—especially measurements or quantities (e.g., dimensions, counts, or other numerical data).

    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
    镲
    -1.98
     semelh
    -1.95
    却不
    -1.77
     artikke
    -1.71
     how
    -1.70
    ૉ
    -1.70
    斃
    -1.67
    brtc
    -1.66
    
    -1.66
     laba
    -1.63
    POSITIVE LOGITS
    ýchod
    1.62
     akin
    1.50
     kekerasan
    1.45
    stdbool
    1.41
    ⁈
    1.40
    Zacks
    1.38
    』『
    1.37
     pernicious
    1.37
     with
    1.36
     растений
    1.35
    Activations Density 0.044%

    No Known Activations