© 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. 113737
    Prev
    Next
    INDEX
    Explanations

    amenable to

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

    The neuron strongly activates on the word “amenable.”

    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
    ーーーー
    -2.84
    翃
    -2.30
     現貨
    -2.27
    replyreport
    -2.22
    ーーー
    -2.17
    摭
    -2.14
    慙
    -2.11
    谖
    -2.11
    selbe
    -2.09
    悒
    -2.08
    POSITIVE LOGITS
     of
    2.52
    鈇
    2.22
    ."
    2.14
    都能
    2.13
    涷
    2.06
    淬
    1.95
    ౭
    1.88
     for
    1.84
    .'
    1.80
    ().
    1.80
    Activations Density 0.000%

    No Known Activations