© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68577
    Prev
    Next
    INDEX
    Explanations

    Brookings Institute, outlays, dysbiosis

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

    The neuron detects words that denote monetary disbursement or outlay.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     are
    -2.25
    または
    -2.25
    他の
    -2.23
    何度
    -2.14
    也非常
    -2.09
    又被
    -2.06
     sorta
    -2.03
    登上
    -2.02
    ))$.
    -2.02
     wounds
    -1.99
    POSITIVE LOGITS
    I
    2.22
    珝
    2.14
    <bos>
    2.02
    präsident
    1.96
    鈇
    1.95
    Flammable
    1.93
    𐄙
    1.91
    彣
    1.86
    妡
    1.86
     and
    1.84
    Activations Density 0.001%

    No Known Activations