© 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. 34-GEMMASCOPE-RES-131K
    7. 32297
    Prev
    Next
    INDEX
    Explanations

    license text `as is` basis

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

    The neuron strongly activates on numeric literals or digit tokens (individual numbers or multi‐digit numbers) in code.

    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
    hydro
    -0.81
    Logs
    -0.81
     george
    -0.80
    erte
    -0.79
    رأ
    -0.78
    惋
    -0.78
     Duch
    -0.77
    ธ
    -0.77
    НС
    -0.77
    geom
    -0.77
    POSITIVE LOGITS
     review
    0.96
     servicios
    0.92
     reviews
    0.88
     znajduje
    0.85
     manage
    0.85
     REVIEW
    0.84
     voici
    0.83
    CZE
    0.79
     breakfast
    0.77
    ema
    0.77
    Activations Density 0.002%

    No Known Activations