© 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. 34255
    Prev
    Next
    INDEX
    Explanations

    sections and technical terms

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

    This neuron activates on inline HTML formatting tags (e.g. <u> and <s>).

    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
     Often
    -2.38
     if
    -2.36
     for
    -2.27
     enhances
    -2.19
     Usually
    -2.13
     Perhaps
    -2.13
     facilitating
    -2.11
     Although
    -2.09
     Almost
    -2.06
     facilitates
    -2.06
    POSITIVE LOGITS
    
    2.53
    mpagne
    2.45
    傒
    2.44
    s
    2.42
     breathtaking
    2.41
     strikingly
    2.36
     exceedingly
    2.34
     beautifully
    2.33
     fantastic
    2.33
     stunning
    2.31
    Activations Density 0.000%

    No Known Activations