© 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. 70447
    Prev
    Next
    INDEX
    Explanations

    instance types like g2.2xlarge

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

    This neuron detects standalone two-digit numeric tokens.

    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
    
    -1.57
     in
    -1.55
    нью
    -1.53
     """",
    -1.47
    鍘
    -1.44
     söyledi
    -1.43
    
    -1.42
    ๓
    -1.41
     становника
    -1.41
    ฿
    -1.41
    POSITIVE LOGITS
    1
    2.53
    2
    2.30
    5
    2.17
    4
    2.17
    3
    1.95
    8
    1.90
    6
    1.90
    7
    1.82
    0
    1.66
    9
    1.63
    Activations Density 0.039%

    No Known Activations