© 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. 22013
    Prev
    Next
    INDEX
    Explanations

    inbreeding, indium, launching

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

    The neuron fires on any token containing the letter sequence “in.”

    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
     Inhalten
    -2.41
    {
    -2.41
     مختلفة
    -2.23
    ྜ
    -2.22
    '
    -2.22
    >
    -2.17
     Mitteln
    -2.16
    ,’
    -2.14
    );
    -2.13
    In
    -2.11
    POSITIVE LOGITS
    櫺
    2.81
    踅
    2.66
     You
    2.59
    潆
    2.27
    跸
    2.25
    翃
    2.23
    趿
    2.22
     tuss
    2.19
    ௅
    2.17
    ções
    2.13
    Activations Density 0.045%

    No Known Activations