© 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. 113297
    Prev
    Next
    INDEX
    Explanations

    lidocaine and LiDAR

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

    This neuron detects occurrences of the letter sequence “lid–” at the start of a term, as in LiDAR or lidocaine.

    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
    -2.69
    2
    -2.31
     tidak
    -2.25
     —
    -2.19
     */
    -2.06
     –
    -2.03
    The
    -2.02
    墬
    -1.98
     і
    -1.96
    人和
    -1.94
    POSITIVE LOGITS
    ";
    2.28
     Перейти
    2.25
    </th>
    2.25
    也会
    2.16
    "--
    2.14
    趼
    2.05
    に来て
    2.05
    "})
    2.00
    蠖
    2.00
     extraordinaire
    1.98
    Activations Density 0.004%

    No Known Activations