© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67698
    Prev
    Next
    INDEX
    Explanations

    java imports and code snippets

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

    The neuron fires primarily on numeric tokens (digits and version numbers).

    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
    ternut
    -1.09
     tracción
    -1.09
     Pozna
    -1.08
    lizes
    -1.06
    ressa
    -1.05
    namental
    -1.05
     Uniwers
    -1.05
     censi
    -1.03
    atized
    -1.02
    買う
    -1.02
    POSITIVE LOGITS
    get
    1.05
     Jordanian
    1.05
     here
    1.04
     in
    1.03
     if
    1.00
     now
    1.00
    ัณฑ
    0.98
    具体的
    0.96
     Sudanese
    0.94
     to
    0.91
    Activations Density 0.000%

    No Known Activations