© 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. 129033
    Prev
    Next
    INDEX
    Explanations

    The neuron is effectively “dead”—it never activates on any of the input tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    associated phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     only
    -1.53
     even
    -1.44
     then
    -1.23
     their
    -1.18
     both
    -1.16
     all
    -1.16
     more
    -1.15
     '%
    -1.09
     many
    -1.07
     often
    -1.06
    POSITIVE LOGITS
    excellents
    1.20
    nade
    1.17
     postulates
    1.16
    Maritime
    1.08
     horrend
    1.07
     těchto
    1.04
    Tils
    1.04
     również
    1.03
     verboten
    1.02
     intrepid
    0.99
    Activations Density 0.000%

    No Known Activations