© 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. 35088
    Prev
    Next
    INDEX
    Explanations

    versus or comparison markers

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

    The neuron flags code-specific tokens—especially numeric literals and non-keyword identifiers (e.g. variable, function, or type 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
     mencionó
    -0.90
    bearded
    -0.90
    acán
    -0.86
    湲
    -0.85
    NewLabel
    -0.85
    に向
    -0.84
    ઃ
    -0.81
    pekte
    -0.80
     Yahweh
    -0.79
    famille
    -0.79
    POSITIVE LOGITS
     Versus
    1.05
     versus
    1.00
    versus
    0.96
    Versus
    0.95
     early
    0.93
     vs
    0.86
     магни
    0.83
     zamiast
    0.79
     תא
    0.79
    vs
    0.78
    Activations Density 0.013%

    No Known Activations