© 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. 84540
    Prev
    Next
    INDEX
    Explanations

    TypeError errors

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

    The neuron flags specialized technical‐ or domain-specific terms (like error names or chemical/material names).

    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
    e
    -3.67
    </strong>
    -3.45
    ка
    -3.41
    a
    -3.27
    ↵
    -2.88
     –
    -2.83
    an
    -2.77
     You
    -2.64
    …
    -2.55
    大概是
    -2.50
    POSITIVE LOGITS
    鑁
    3.48
    鬭
    3.06
    纛
    2.98
     думал
    2.75
    voorbeeld
    2.75
     gantung
    2.73
    詎
    2.73
    訫
    2.70
    呿
    2.67
    墻
    2.64
    Activations Density 0.006%

    No Known Activations