© 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. 34-GEMMASCOPE-RES-131K
    7. 78801
    Prev
    Next
    INDEX
    Explanations

    xml tags followed by greater than

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

    The neuron fires on numeric values—especially version, scale, or configuration numbers—embedded in structured files.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     this
    -1.52
     before
    -1.38
     not
    -1.34
     even
    -1.30
     has
    -1.30
     because
    -1.27
     will
    -1.27
     then
    -1.25
     strangely
    -1.21
     should
    -1.19
    POSITIVE LOGITS
    mbgg
    1.30
    particularly
    1.28
     Dinas
    1.24
     wondrous
    1.22
    푉
    1.21
     conster
    1.20
     horrid
    1.15
     joyous
    1.15
    γα
    1.14
    creating
    1.12
    Activations Density 0.009%

    No Known Activations