© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103699
    Prev
    Next
    INDEX
    Explanations

    individuals and their variations

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

    The neuron detects mentions of "individuals" in scientific texts, particularly in biology and medical research contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on multi‐digit numeric tokens (e.g. sample sizes or counts) 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_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
    }$
    -2.42
    -2.02
     stalwart
    -1.85
    癭
    -1.78
    
    -1.76
    ᵴ
    -1.76
     betroffen
    -1.73
     добавил
    -1.70
    🧌
    -1.66
    耵
    -1.66
    POSITIVE LOGITS
    .
    2.19
    </h2>
    2.08
    酲
    1.86
     other
    1.77
     Surprisingly
    1.70
     Also
    1.70
     Following
    1.68
    Surprisingly
    1.65
     Additionally
    1.62
    谞
    1.62
    Activations Density 0.022%

    No Known Activations