© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34592
    Prev
    Next
    INDEX
    Explanations

    document headings and structure

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

    The neuron detects LaTeX package and class names in the document preamble.

    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
     for
    -1.72
     on
    -1.70
     all
    -1.59
     several
    -1.58
     had
    -1.55
     having
    -1.53
     even
    -1.52
     at
    -1.48
     these
    -1.46
     only
    -1.45
    POSITIVE LOGITS
     strikingly
    1.41
     colossal
    1.25
     famed
    1.24
     captivating
    1.21
     breathtaking
    1.17
     magnific
    1.16
     flamboyant
    1.16
     poign
    1.14
     momentous
    1.14
     tarifs
    1.14
    Activations Density 0.000%

    No Known Activations