© 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. 58776
    Prev
    Next
    INDEX
    Explanations

    URLs and parameters

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

    The neuron is essentially flagging programming‐code tokens (e.g. imports, function names, identifiers, URLs)—i.e. spotting code snippets.

    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
    းက
    -0.88
     kommende
    -0.85
     Linger
    -0.84
    Techniques
    -0.83
    scooter
    -0.81
    ablanca
    -0.80
    ーん
    -0.78
    eti
    -0.78
    
    -0.78
    光景
    -0.76
    POSITIVE LOGITS
     url
    3.16
    url
    3.00
     URL
    2.67
    URL
    2.64
    Url
    2.44
     Url
    1.97
     uri
    1.76
     params
    1.74
     URI
    1.73
    uri
    1.72
    Activations Density 0.056%

    No Known Activations