© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8602
    Prev
    Next
    INDEX
    Explanations

    obtain a copy

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

    This neuron activates on the all-caps header and key legal terms used in formal public-notice or foreclosure-sale announcements.

    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
     bunda
    -1.79
     impresora
    -1.61
     tunik
    -1.55
     kokos
    -1.52
     dégust
    -1.50
     augus
    -1.49
     kazak
    -1.49
     déclar
    -1.48
     médicaments
    -1.48
     déclen
    -1.48
    POSITIVE LOGITS
     its
    2.00
     at
    1.97
     by
    1.81
     in
    1.71
     for
    1.67
     if
    1.66
     has
    1.62
     on
    1.47
     from
    1.43
     it
    1.41
    Activations Density 0.127%

    No Known Activations