© 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. 22-GEMMASCOPE-RES-131K
    7. 64892
    Prev
    Next
    INDEX
    Explanations

    speaker systems

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

    The neuron activates on mentions of audio or sound hardware and related technical terms (e.g. speakers, audio output, drivers, power levels).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    .‏
    -1.29
     солнца
    -1.25
     ayudarte
    -1.15
     вокруг
    -1.14
    %">
    -1.14
     hidratante
    -1.13
     Tiểu
    -1.13
    обзор
    -1.11
     \%$,
    -1.11
     tendo
    -1.11
    POSITIVE LOGITS
     output
    1.27
     törvény
    1.21
    вѣ
    1.21
    enderal
    1.20
    输出
    1.20
     杨
    1.19
    不動産
    1.17
    phany
    1.14
    output
    1.13
    zości
    1.13
    Activations Density 0.043%

    No Known Activations