© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38692
    Prev
    Next
    INDEX
    Explanations

    recruiting people or entities

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

    The neuron detects occurrences of the root “recruit” in any of its inflected forms.

    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
     Descri
    -2.50
    玏
    -2.42
    }$
    -2.42
     catapult
    -2.28
     entail
    -2.13
    –
    -2.13
    dė
    -2.09
    os
    -2.08
    )」
    -2.02
     crux
    -1.99
    POSITIVE LOGITS
    狆
    2.67
     ヌード
    2.63
    Ꮵ
    2.45
    茕
    2.44
     глазах
    2.39
     eier
    2.39
     tyn
    2.38
     ソックス
    2.36
    跸
    2.34
     sio
    2.31
    Activations Density 0.006%

    No Known Activations