© 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. 99389
    Prev
    Next
    INDEX
    Explanations

    noise and sound levels

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

    The neuron is triggered by technical references to “noise” (and related terms or measures of sound intensity).

    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
    
    -1.23
    kanie
    -1.21
    oires
    -1.16
    yszer
    -1.15
    rozco
    -1.09
    에
    -1.08
     omtrent
    -1.05
     Coli
    -1.05
    straat
    -1.05
     beslut
    -1.05
    POSITIVE LOGITS
    の方も
    1.17
    主題
    1.16
    キン
    1.14
     louder
    1.13
    LER
    1.12
     loud
    1.10
     zarówno
    1.09
    をかけ
    1.09
     wcześniej
    1.09
     生
    1.07
    Activations Density 0.054%

    No Known Activations