© 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. 43660
    Prev
    Next
    INDEX
    Explanations

    talents and abilities

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

    The neuron activates on mentions of “talent” (and its variants like “talents” or “talented”) 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
    呿
    -2.31
    哢
    -2.23
    Nacimiento
    -2.19
    谂
    -2.17
    ៦
    -2.14
    歃
    -2.11
    
    -2.09
    ☗
    -2.05
    韪
    -2.05
    闥
    -2.02
    POSITIVE LOGITS
    .
    3.31
    </h2>
    2.55
    ↵↵
    2.52
    )
    2.48
    A
    2.41
    他也
    2.20
    the
    2.14
    </h4>
    1.99
    Also
    1.98
    </sup>
    1.94
    Activations Density 0.003%

    No Known Activations