© 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. 10-GEMMASCOPE-RES-131K
    7. 105837
    Prev
    Next
    INDEX
    Explanations

    numbers following hyphens or periods

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

    The neuron is sensitive to standalone numeric tokens (numbers, digits, and numeric punctuation).

    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
    0
    -4.16
    ↵↵↵
    -2.88
    9
    -2.66
    ↵↵
    -2.55
     [
    -2.52
    f
    -2.52
     But
    -2.36
     этими
    -2.33
    4
    -2.31
                    
    -2.23
    POSITIVE LOGITS
    乀
    2.92
    鸶
    2.73
     dévelo
    2.61
    桫
    2.56
    ⢓
    2.53
    を書
    2.52
    亍
    2.47
    琑
    2.45
    乄
    2.42
     BASIN
    2.41
    Activations Density 0.363%

    No Known Activations