© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58936
    Prev
    Next
    INDEX
    Explanations

    URLs with numbers and slashes

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

    This neuron is triggered by numeric tokens (digit sequences), especially those used as identifiers or date components in URLs.

    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
     mouseY
    -1.77
     you
    -1.67
     paramInt
    -1.51
    biendo
    -1.45
    ГИ
    -1.41
     endforeach
    -1.40
    rabi
    -1.40
     CGRect
    -1.39
    墮
    -1.38
     localObject
    -1.38
    POSITIVE LOGITS
     are
    1.88
     -
    1.63
    −/−
    1.58
     fortific
    1.52
     málaga
    1.51
     minuten
    1.50
     그의
    1.49
     cerâmica
    1.48
    ”)
    1.46
     bringe
    1.44
    Activations Density 0.041%

    No Known Activations