© 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. 128110
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on short technical acronyms and abbreviations (especially uppercase/math‐rule names and code identifiers).

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

    specific names and terms

    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
     berichten
    -1.08
    preferably
    -1.06
     impromptu
    -1.04
     verp
    -1.01
     EXCLUSIVE
    -1.00
    berra
    -1.00
    ##
    -0.99
    だけは
    -0.99
    模様
    -0.98
     frumo
    -0.98
    POSITIVE LOGITS
     when
    1.60
     with
    1.52
     our
    1.44
     for
    1.30
     from
    1.26
     other
    1.23
     like
    1.22
     if
    1.21
     any
    1.20
     beantworten
    1.18
    Activations Density 0.003%

    No Known Activations