© 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. 129339
    Prev
    Next
    INDEX
    Explanations

    www and web paths

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

    The neuron fires on occurrences of the character sequence “www” (e.g. in domain names, URL paths, or media‐type strings).

    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
     contain
    -2.02
     становится
    -1.72
     do
    -1.65
     are
    -1.59
     has
    -1.52
     آیا
    -1.47
    L
    -1.45
    よい
    -1.43
    ський
    -1.41
    '
    -1.41
    POSITIVE LOGITS
    ים
    1.96
    錾
    1.95
     produkter
    1.88
    髕
    1.78
    媄
    1.78
    ŚĆ
    1.73
     剤
    1.70
     aktiviteter
    1.70
    ی
    1.70
    ynchrotron
    1.65
    Activations Density 0.005%

    No Known Activations