© 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. 22-GEMMASCOPE-RES-131K
    7. 15738
    Prev
    Next
    INDEX
    Explanations

    links to code snippets

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

    This neuron responds to section‐heading or title tokens—particularly those that begin lines or start with a capital letter (e.g. “Links,” “Food,” “In,” etc.).

    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
     Vorschriften
    -1.32
    チール
    -1.03
     équipé
    -0.99
     éto
    -0.98
     Bestimmungen
    -0.98
     réjou
    -0.97
    ättning
    -0.96
    
    -0.95
     Grâce
    -0.94
    ÍC
    -0.93
    POSITIVE LOGITS
     because
    1.38
     will
    1.14
     this
    1.12
     over
    1.11
     may
    1.05
     some
    1.03
     help
    1.03
     most
    1.02
     its
    1.01
     so
    1.00
    Activations Density 0.052%

    No Known Activations