© 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. 130014
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on short alphanumeric identifier tokens (e.g. small acronyms, code‐style names or gene/protein IDs) rather than on ordinary words.

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

    abbreviations and numbers

    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
     unquestionably
    -1.44
    </sub>
    -1.44
     enhanced
    -1.39
     highly
    -1.34
     amusing
    -1.32
    vál
    -1.32
     certainly
    -1.30
    ॄ
    -1.29
    </h3>
    -1.27
     manages
    -1.27
    POSITIVE LOGITS
    </b>
    1.48
     derselben
    1.38
     myriad
    1.38
    iedy
    1.34
     fiasco
    1.30
     MANY
    1.30
     debacle
    1.28
     restent
    1.27
    рую
    1.26
    龶
    1.25
    Activations Density 0.237%

    No Known Activations