© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 29176
    Prev
    Next
    INDEX
    Explanations

    noise, vibration, and interference

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

    The neuron activates on words describing physical contact or impact between objects (e.g. rattles, bounce, hits, against).

    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
     vendar
    -1.17
    paroles
    -1.14
     to
    -1.14
    เพื่อ
    -1.08
     VIDEOTAPE
    -1.07
    出了一
    -1.05
    lanması
    -1.05
     nedenle
    -1.05
     พร้อม
    -1.04
     Histórico
    -1.04
    POSITIVE LOGITS
     everything
    1.22
     your
    1.20
    "));
    1.19
    很容易
    1.16
    ungkin
    1.14
    </blockquote>
    1.09
     durante
    1.06
    一切
    1.05
    ynı
    1.04
     podczas
    1.03
    Activations Density 0.091%

    No Known Activations