© 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. 10-GEMMASCOPE-RES-131K
    7. 3704
    Prev
    Next
    INDEX
    Explanations

    file extensions

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

    This neuron detects numeric identifiers in file‐ or template‐include paths (i.e. the digits in filenames).

    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
    -
    -2.70
    :
    -2.58
    ...........
    -2.36
    ............
    -2.30
    .........
    -2.30
    様々な
    -2.27
    '/
    -2.22
    ¹
    -2.11
     the
    -2.11
    .............
    -2.06
    POSITIVE LOGITS
     usually
    2.75
     occasionally
    2.58
    ſelves
    2.53
     sometimes
    2.52
     generally
    2.44
    なのかな
    2.38
     always
    2.36
     actually
    2.30
     especially
    2.28
     now
    2.27
    Activations Density 0.121%

    No Known Activations