© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30565
    Prev
    Next
    INDEX
    Explanations

    Elton, Clark, Kendal, Watford, Elton Mangoma

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

    The main thing this neuron does is find numeric tokens (e.g. standalone numbers, dates, counts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    calf
    -0.83
    ratie
    -0.73
    ].[
    -0.70
    creature
    -0.68
    decomposition
    -0.65
     пад
    -0.65
    蒙古
    -0.62
    ⏲
    -0.62
     Pa
    -0.62
     làn
    -0.61
    POSITIVE LOGITS
     Elton
    1.52
     Watford
    1.27
    Elton
    1.20
     Rocket
    1.18
    Rocket
    1.15
     Farewell
    1.09
    elton
    1.02
     EJ
    0.92
    Farewell
    0.89
     Burnley
    0.88
    Activations Density 0.011%

    No Known Activations