© 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. 60797
    Prev
    Next
    INDEX
    Explanations

    Emerson, Everett, Magnolia, adjunct

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

    The neuron responds strongly to any single token that’s exactly seven letters long.

    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
    
    -2.89
     standout
    -2.67
     Ähn
    -2.55
    瑒
    -2.47
     recibiendo
    -2.47
    鹋
    -2.45
    皷
    -2.41
     weiterer
    -2.38
     similarly
    -2.36
    abrir
    -2.36
    POSITIVE LOGITS
    ”
    3.00
    </td>
    3.00
    U
    2.84
    $
    2.56
    );
    2.50
    耵
    2.44
    </
    2.41
    苳
    2.41
    使って
    2.34
    Z
    2.34
    Activations Density 0.003%

    No Known Activations