© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48365
    Prev
    Next
    INDEX
    Explanations

    Q: questions and code snippets

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

    The neuron is highly sensitive to numeric tokens (especially version numbers and other numeric literals) 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
     Reggae
    -0.87
     reggae
    -0.82
    タウン
    -0.81
    komt
    -0.80
     oregano
    -0.73
    kubectl
    -0.71
    èdent
    -0.71
     rechargeable
    -0.71
    Blender
    -0.71
    Jakarta
    -0.71
    POSITIVE LOGITS
     Bordeaux
    0.87
    siapkan
    0.79
    createComponent
    0.79
    情緒
    0.75
     있습니다
    0.74
     ujednoznacz
    0.73
     jakim
    0.73
    olm
    0.72
     Blue
    0.72
     Eigent
    0.71
    Activations Density 0.008%

    No Known Activations