© 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. 34-GEMMASCOPE-RES-131K
    7. 30230
    Prev
    Next
    INDEX
    Explanations

    common phrase pairings

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

    The neuron responds strongly to topical, content-bearing words (nouns, verbs, adjectives) in a design‐discussion context, essentially flagging key “content” tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Francus
    -1.52
     Strukt
    -1.52
    fahrzeug
    -1.51
     Katalog
    -1.42
     kompati
    -1.36
     toul
    -1.34
    iç
    -1.34
     hej
    -1.34
     lutter
    -1.31
     fuis
    -1.30
    POSITIVE LOGITS
     I
    1.75
     of
    1.73
     ,
    1.60
     no
    1.55
     )
    1.52
     or
    1.49
     maybe
    1.45
     especially
    1.45
     in
    1.44
     oh
    1.44
    Activations Density 0.005%

    No Known Activations