© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54299
    Prev
    Next
    INDEX
    Explanations

    method and function definitions

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects square-bracket delimiters (i.e. tokens “\[” and “\]”) used for lists or array‐style notation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    jący
    -1.11
    Péri
    -1.10
     magnifiques
    -1.09
    aktifkan
    -1.08
     Tratado
    -1.08
     niego
    -1.07
    JAMIN
    -1.05
    久しぶりの
    -1.03
    mesin
    -1.02
    üme
    -1.02
    POSITIVE LOGITS
     to
    1.66
     functions
    1.18
     methods
    1.16
     tests
    1.15
     bett
    1.11
     roleId
    1.09
    get
    1.09
    》、《
    1.09
    <#
    1.07
     hong
    1.02
    Activations Density 0.009%

    No Known Activations