© 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. 16585
    Prev
    Next
    INDEX
    Explanations

    specific devices or types

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

    The neuron selectively fires on individual specialized technical terms—like chemical names, taxonomic or biological categories, dosing‐form words, OS or protocol names, and HTTP method keywords.

    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
     fann
    -0.99
    Bibliote
    -0.98
    んだよね
    -0.91
    slot
    -0.91
     intelligen
    -0.90
     activer
    -0.90
    はずです
    -0.89
     maint
    -0.89
    ダウン
    -0.87
    attuale
    -0.87
    POSITIVE LOGITS
     szczególnie
    1.08
     especially
    1.05
     particularly
    0.97
    usura
    0.93
     élevés
    0.93
    metti
    0.92
     especialmente
    0.91
     gyerme
    0.91
    presso
    0.88
     przypadku
    0.88
    Activations Density 0.076%

    No Known Activations