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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39375
    Prev
    Next
    INDEX
    Explanations

    character and its description

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

    The neuron fires strongly on major abstract‐noun keywords (e.g. “character,” “cult,” “personality,” “institution”) that label central concepts or headings.

    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
    sudadera
    -1.64
     uova
    -1.52
    atação
    -1.50
    歃
    -1.50
    Teknik
    -1.49
    苼
    -1.49
    ꯹
    -1.45
    Gön
    -1.43
    ！"
    -1.41
    蕖
    -1.40
    POSITIVE LOGITS
    </h2>
    1.77
    ;
    1.73
     of
    1.65
    ’
    1.64
    </h1>
    1.52
    たちに
    1.45
    l
    1.41
    :
    1.36
    ]
    1.34
     типи
    1.26
    Activations Density 0.022%

    No Known Activations