© 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. 34-GEMMASCOPE-RES-131K
    7. 62976
    Prev
    Next
    INDEX
    Explanations

    course sections

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

    The neuron is strongly activated by numeric tokens (especially multi‐digit numbers and digit‐containing identifiers).

    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
    様
    -0.79
    Kni
    -0.75
     Roku
    -0.74
     връ
    -0.71
    年生
    -0.71
     PEC
    -0.70
     indign
    -0.69
     تي
    -0.69
     decrees
    -0.68
     ULT
    -0.68
    POSITIVE LOGITS
     section
    1.98
     sections
    1.92
    Sections
    1.51
     Section
    1.46
    Section
    1.45
     sección
    1.41
     Sections
    1.38
    sections
    1.35
     instructor
    1.31
    section
    1.25
    Activations Density 0.030%

    No Known Activations