© 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. 113812
    Prev
    Next
    INDEX
    Explanations

    Leonardo DiCaprio or Da Vinci

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

    The neuron activates on occurrences of the proper name “Leonardo DiCaprio.”

    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
    '
    -2.70
    r
    -2.59
    \
    -2.48
    .”
    -2.38
    to
    -2.33
    u
    -2.31
    at
    -2.27
    al
    -2.09
    $-
    -2.08
    『
    -2.08
    POSITIVE LOGITS
     используются
    2.42
     variedades
    2.25
    ではまた
    2.17
    轳
    2.16
    ſtre
    2.09
    숱
    2.06
    艫
    2.05
    튿
    2.05
     Augenblick
    2.00
    âncias
    2.00
    Activations Density 0.003%

    No Known Activations