© 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. 68667
    Prev
    Next
    INDEX
    Explanations

    elicit something

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

    The neuron detects occurrences of the root “elic” (as in elicit, elicited, eliciting, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     we
    -2.67
     You
    -2.48
    遢
    -2.19
    橚
    -2.16
    褫
    -2.13
    ي
    -2.11
    you
    -2.09
    你还
    -2.09
    媄
    -2.06
     einzigen
    -2.05
    POSITIVE LOGITS
    韡
    2.17
    涐
    2.16
    谖
    2.11
     fuertemente
    2.09
    歘
    2.08
     supuestamente
    2.02
     fejl
    2.00
    𓇼
    1.98
     inicialmente
    1.96
     nových
    1.91
    Activations Density 0.008%

    No Known Activations