© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40513
    Prev
    Next
    INDEX
    Explanations

    job title, department, location

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

    The neuron activates on standalone numeric tokens—especially decimal or large numbers—that typically appear as metadata (e.g. scores, years, identifiers) rather than regular text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     resistentes
    -1.95
    continues
    -1.88
     literalmente
    -1.81
    colección
    -1.80
    finds
    -1.79
     menek
    -1.78
     Detalles
    -1.77
    
    -1.77
     natuurlijk
    -1.74
     Yorker
    -1.73
    POSITIVE LOGITS
     of
    2.67
    the
    1.99
    on
    1.98
    from
    1.94
     from
    1.91
     not
    1.85
     to
    1.84
     While
    1.80
     Although
    1.73
     within
    1.65
    Activations Density 0.081%

    No Known Activations