© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 11861
    Prev
    Next
    INDEX
    Explanations

    README file extensions

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

    The neuron is triggered by file names and file‐path tokens (including wildcard patterns) that contain a dot and an extension.

    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
    kohl
    -0.75
    醣
    -0.74
    젯
    -0.73
     caráter
    -0.73
    calyptic
    -0.72
    SKU
    -0.71
     Erwart
    -0.71
     hearing
    -0.71
     settings
    -0.69
    诺
    -0.69
    POSITIVE LOGITS
     README
    1.80
     readme
    1.63
    README
    1.60
    readme
    1.34
     Read
    1.28
    Read
    1.25
     INSTALL
    1.25
     READ
    1.22
    txt
    1.05
    INSTALL
    1.03
    Activations Density 0.209%

    No Known Activations