© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107140
    Prev
    Next
    INDEX
    Explanations

    boolean values and version numbers

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

    The neuron activates on literal values (numeric constants and boolean literals) in code or config.

    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
     gruesome
    -1.38
     immense
    -1.36
     magnificent
    -1.35
     then
    -1.33
     delightfully
    -1.32
     astounding
    -1.30
     breathtaking
    -1.28
     dreadful
    -1.27
     wonderfully
    -1.25
     amazing
    -1.24
    POSITIVE LOGITS
     this
    1.52
     because
    1.45
     even
    1.38
     allows
    1.32
     what
    1.29
     so
    1.29
     enables
    1.27
     should
    1.25
     makes
    1.23
     reasonably
    1.23
    Activations Density 0.084%

    No Known Activations