© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59578
    Prev
    Next
    INDEX
    Explanations

    yeast

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

    The neuron activates for the '@' symbol, particularly when it appears in URLs on social media platforms and websites.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    
    -3.39
    辚
    -3.20
    ፨
    -3.19
    ჻
    -2.89
    
    -2.84
    䊐
    -2.80
    .}
    -2.72
    akterysty
    -2.72
    .
    -2.69
    〠
    -2.67
    POSITIVE LOGITS
    '
    3.70
     they
    3.02
    k
    2.58
    a
    2.53
    UAWEI
    2.53
     itſelf
    2.52
    把它
    2.41
    “
    2.41
    ir
    2.39
    C
    2.39
    Activations Density 0.001%

    No Known Activations