© 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. 101231
    Prev
    Next
    INDEX
    Explanations

    , filed, include, Produced, Circulatory, comparison

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

    numbers, commas, and formatting characters in technical or code documents.

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

    The neuron activates on numeric tokens (numbers or numeric literals) 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
    .
    -2.16
    ’
    -1.91
    </h3>
    -1.84
    t
    -1.83
     etwas
    -1.82
     utterly
    -1.82
                    
    -1.80
    (
    -1.78
           
    -1.77
    On
    -1.75
    POSITIVE LOGITS
     horarios
    2.45
     estándares
    2.20
    ."
    2.11
     größe
    2.08
     流れ
    2.02
    🫅
    1.99
     perfiles
    1.93
    alisco
    1.92
     eenvoudig
    1.92
     eigenlijk
    1.91
    Activations Density 0.000%

    No Known Activations