© 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. 72148
    Prev
    Next
    INDEX
    Explanations

    giving advice and recommendations

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

    The neuron activates on verbs and nouns expressing advice or recommendations (e.g., recommend, suggest, urge, advise).

    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
    umbledore
    -1.60
    後記
    -1.51
     одна
    -1.41
     elevating
    -1.38
    utella
    -1.35
     all
    -1.34
    邹
    -1.34
     таким
    -1.34
    における
    -1.32
    xFE
    -1.31
    POSITIVE LOGITS
     fossero
    1.90
    你
    1.70
    kk
    1.67
     getNombre
    1.64
     لأنه
    1.51
    you
    1.48
     ſi
    1.45
     内衣
    1.44
    我们
    1.41
    ſtra
    1.41
    Activations Density 0.054%

    No Known Activations