© 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. 75493
    Prev
    Next
    INDEX
    Explanations

    gear shifting and controls

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

    The neuron detects technical terms related to vehicle transmissions and gear‐shifting mechanisms.

    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
    CELLANEOUS
    -1.31
    '/',
    -1.20
    ेमाल
    -1.19
    ivotopis
    -1.19
    larında
    -1.16
    場の
    -1.13
    lanations
    -1.12
     begeistert
    -1.11
     Garda
    -1.10
    ník
    -1.09
    POSITIVE LOGITS
    </h5>
    1.20
    حياته
    1.20
     damaligen
    1.17
     Only
    1.13
     with
    1.09
    </td>
    1.07
     Before
    1.07
     Even
    1.06
     the
    1.03
     Hence
    1.03
    Activations Density 0.038%

    No Known Activations