© 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. 64719
    Prev
    Next
    INDEX
    Explanations

    results and outcomes

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

    The neuron is highly activated by numeric tokens (number literals or digit sequences).

    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
    問
    -0.87
    DllImport
    -0.82
    Dispatch
    -0.81
     commut
    -0.80
     Dispatch
    -0.77
    quartered
    -0.77
    ateľ
    -0.76
    çeği
    -0.75
    踝
    -0.75
    endale
    -0.74
    POSITIVE LOGITS
     RESULT
    1.45
    RESULT
    1.33
    setResult
    1.32
     resultCode
    1.05
     result
    0.79
     getResult
    0.74
    Ok
    0.74
    OK
    0.73
     improving
    0.71
    DialogResult
    0.70
    Activations Density 0.008%

    No Known Activations