© 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. 112454
    Prev
    Next
    INDEX
    Explanations

    talent

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

    The neuron activates on occurrences of the word “talent” (in any capitalization).

    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
    os
    -2.52
    饧
    -2.31
    
    -2.23
    銫
    -2.22
    闥
    -2.20
    gebras
    -2.19
    に
    -2.17
     целью
    -2.14
    韪
    -2.13
    
    -2.11
    POSITIVE LOGITS
    .
    3.33
    ⚣
    2.67
    </sup>
    2.53
     you
    2.41
    又在
    2.33
    垆
    2.23
    彞
    2.22
    ⚋
    2.22
     帅气
    2.17
    认真
    2.14
    Activations Density 0.003%

    No Known Activations