© 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. 129593
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on tokens that begin with an uppercase letter (e.g. type names, keywords, or proper-case words).

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

    legal and technical contexts

    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
    CCION
    -1.16
     countless
    -1.14
    ⼆
    -1.09
    CCIÓN
    -1.06
     quaint
    -1.06
     people
    -1.05
     sehr
    -1.05
    inę
    -1.04
    obbies
    -1.02
     had
    -1.01
    POSITIVE LOGITS
    obviously
    1.30
     -
    1.27
    猛地
    1.19
     pn
    1.16
    Ï
    1.16
    졍
    1.16
     homicidio
    1.15
     $
    1.13
     logiciels
    1.13
     {,
    1.10
    Activations Density 0.016%

    No Known Activations