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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9511
    Prev
    Next
    INDEX
    Explanations

    legal citations or URLs

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

    This neuron activates on snippets of source code—especially Java keywords, class/method names, punctuation, and other code‐specific 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_22/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
     their
    -1.80
     it
    -1.53
     encanto
    -1.50
     only
    -1.49
     its
    -1.48
     would
    -1.46
     all
    -1.42
     they
    -1.29
    iteln
    -1.24
     there
    -1.20
    POSITIVE LOGITS
     unseres
    1.41
     также
    1.34
     обычно
    1.27
     プリント
    1.27
     unserer
    1.27
    Hilsen
    1.20
     firs
    1.20
    drücke
    1.19
    Steg
    1.18
    remacy
    1.18
    Activations Density 0.003%

    No Known Activations