© 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. 129581
    Prev
    Next
    INDEX
    Explanations

    The neuron never activates on any input and thus does not detect any pattern.

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

    code syntax elements

    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
     in
    -1.51
     this
    -1.45
     with
    -1.44
     that
    -1.35
     for
    -1.33
     all
    -1.28
     from
    -1.26
    夙
    -1.23
     which
    -1.22
     such
    -1.22
    POSITIVE LOGITS
     firs
    1.19
     ,.
    1.16
     abd
    1.15
     foll
    1.14
    bereiche
    1.13
     marvelous
    1.13
     verschiedener
    1.11
     häufiger
    1.11
     genauer
    1.11
     passend
    1.09
    Activations Density 0.000%

    No Known Activations