© 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. 72934
    Prev
    Next
    INDEX
    Explanations

    of President, An excised, New Video

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

    This neuron activates on markdown bold markers (the “**” delimiters used for boldface).

    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
    \
    -2.13
    .”
    -2.02
    ).
    -2.02
    -
    -1.87
     demás
    -1.70
     other
    -1.70
    \_
    -1.65
    */
    -1.58
     an
    -1.55
    If
    -1.55
    POSITIVE LOGITS
    żeli
    1.81
     ウィメンズ
    1.72
     白い
    1.70
     martens
    1.66
    gangen
    1.66
     soms
    1.61
     gått
    1.60
    liegende
    1.57
    zembro
    1.57
    自己
    1.57
    Activations Density 0.000%

    No Known Activations