© 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. 22-GEMMASCOPE-RES-131K
    7. 64431
    Prev
    Next
    INDEX
    Explanations

    anatomical and medical terms

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

    abstract concepts related to physical or mental conditions and states like health, economy, life circumstances.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    The neuron strongly activates on the final content word before a paragraph or segment break, i.e. it detects sentence‐ or segment‐final nouns or key “stop” words.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     to
    -1.20
     then
    -1.13
     ontdek
    -1.04
    ,
    -1.01
     aldus
    -0.95
    .",
    -0.94
    その他の
    -0.93
    已然
    -0.92
    wählen
    -0.91
     tevreden
    -0.91
    POSITIVE LOGITS
     Redacción
    1.12
    ARAN
    1.07
     gyak
    1.01
    
    0.99
    焼く
    0.99
    唷
    0.98
    ﾍ
    0.94
    ऎ
    0.94
    íg
    0.91
     jopa
    0.91
    Activations Density 0.075%

    No Known Activations