© 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. 7270
    Prev
    Next
    INDEX
    Explanations

    folklore and Ft

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

    The neuron sharply activates on the term “folklore” (and its close variants), flagging mentions of folklore.

    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
    {
    -2.78
    a
    -2.58
    /
    -2.56
    k
    -2.44
    N
    -2.41
    y
    -2.36
    (
    -2.25
    蕷
    -2.23
    d
    -2.23
     légère
    -2.23
    POSITIVE LOGITS
    緜
    2.67
    摃
    2.67
    鞮
    2.45
    诓
    2.34
    鸶
    2.33
    婓
    2.28
    お店の
    2.25
     недавно
    2.20
     podían
    2.09
     sayap
    2.06
    Activations Density 0.001%

    No Known Activations