© 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. 10-GEMMASCOPE-RES-131K
    7. 41042
    Prev
    Next
    INDEX
    Explanations

    included / includes

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

    The neuron activates on formal technical or academic report–style terms (e.g. “analysis,” “investigation,” “techniques,” “of,” “which”), indicating it’s looking for scientific-writing language.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     there
    -2.47
     it
    -2.28
     this
    -1.95
    there
    -1.88
     if
    -1.78
     when
    -1.72
     There
    -1.64
    when
    -1.63
     before
    -1.62
     or
    -1.52
    POSITIVE LOGITS
     stratég
    1.66
     horrifying
    1.63
     Entfer
    1.63
    appears
    1.58
    genodigd
    1.56
    pherds
    1.55
     kağıdı
    1.54
     WHICH
    1.53
    probably
    1.52
     MAKES
    1.52
    Activations Density 0.214%

    No Known Activations