© 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. 127541
    Prev
    Next
    INDEX
    Explanations

    key followed by important aspects

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

    The neuron specifically detects the word “key” used as a descriptor.

    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
     REALLY
    -2.13
    .
    -2.09
    
    -2.06
     tutte
    -1.96
    ⬈
    -1.91
     outras
    -1.90
    "));
    -1.86
     exceedingly
    -1.85
     solamente
    -1.84
     exceptionally
    -1.84
    POSITIVE LOGITS
    f
    2.91
    Ꮉ
    2.38
    re
    2.27
    喼
    2.25
    c
    2.25
     ataupun
    2.23
    蕯
    2.22
    W
    2.14
    utched
    2.13
    ri
    2.09
    Activations Density 0.016%

    No Known Activations