© 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. 10-GEMMASCOPE-RES-131K
    7. 112167
    Prev
    Next
    INDEX
    Explanations

    code or URLs separators

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

    URLs or web addresses, particularly those appearing after parentheses or in technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron fires strongly on punctuation tokens (commas, colons, semicolons, parentheses, periods, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Reſ
    -2.02
    渽
    -1.73
    事が
    -1.70
    $
    -1.70
    涐
    -1.68
    桝
    -1.60
    
    -1.55
     proveniente
    -1.55
     ใช้
    -1.54
    侂
    -1.54
    POSITIVE LOGITS
     are
    2.03
     Sometimes
    1.89
     Generally
    1.84
     Honestly
    1.83
     If
    1.80
    tığı
    1.77
     Sadly
    1.76
     Apparently
    1.73
     variadas
    1.73
    ússia
    1.72
    Activations Density 0.035%

    No Known Activations