© 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. 98586
    Prev
    Next
    INDEX
    Explanations

    code, parameters, variables

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

    This neuron fires on programming‐style identifiers and field names (e.g. JSON keys, XML tags, or code variable/class names).

    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
     pantalon
    -1.07
     colheres
    -1.03
     peluche
    -1.03
     pantal
    -0.98
     poliuret
    -0.97
     urat
    -0.97
     consé
    -0.96
    reasonably
    -0.95
    LÄ
    -0.95
     actrices
    -0.94
    POSITIVE LOGITS
    If
    1.05
     If
    0.99
    _
    0.94
    S
    0.92
    n
    0.91
    b
    0.88
    k
    0.88
     or
    0.86
    t
    0.85
     did
    0.84
    Activations Density 0.040%

    No Known Activations