© 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. 7137
    Prev
    Next
    INDEX
    Explanations

    repeat clusters, functions, f, rat

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

    This neuron activates on tokens containing the letter “f.”

    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
    {
    -2.41
    最后由
    -2.39
    韪
    -2.33
    鉝
    -2.28
    によって
    -2.23
    龑
    -2.14
    罽
    -2.14
     Для
    -2.11
    ities
    -2.08
    carteles
    -2.08
    POSITIVE LOGITS
    ’
    3.77
    需要
    2.53
     merav
    2.52
    能在
    2.48
     assorted
    2.33
    uſe
    2.30
    𓐍
    2.28
    鷽
    2.28
    begin
    2.27
    uksen
    2.25
    Activations Density 0.391%

    No Known Activations