© 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. 16028
    Prev
    Next
    INDEX
    Explanations

    youtube links in code

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

    The neuron strongly activates on code‐block delimiters (e.g. the triple backtick fences) and similar large comment or code‐section markers.

    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
     in
    -2.27
    la
    -1.70
    i
    -1.63
    それから
    -1.55
     (
    -1.55
    c
    -1.49
    
    -1.48
    p
    -1.42
    ti
    -1.41
     mest
    -1.41
    POSITIVE LOGITS
    為に
    1.84
    鵟
    1.72
    鶩
    1.67
     rispet
    1.64
     verwacht
    1.63
    IBLIO
    1.62
     gestartet
    1.59
    會有
    1.58
    abriel
    1.55
     milieux
    1.55
    Activations Density 0.001%

    No Known Activations