© 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. 9702
    Prev
    Next
    INDEX
    Explanations

    leopard

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

    The neuron consistently detects the word “leopard” (in any context—animal species, OS X version, place names, etc.).

    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
    櫺
    -2.31
    跸
    -1.94
    ︐
    -1.88
     jezt
    -1.87
    pecabe
    -1.84
    ].
    -1.81
    .\"
    -1.77
    ﮯ
    -1.76
    魠
    -1.74
    睒
    -1.70
    POSITIVE LOGITS
    ’
    2.33
     ‘
    1.95
     have
    1.91
     Because
    1.78
    、
    1.77
    
    1.53
     What
    1.52
    <
    1.50
     of
    1.46
    ÁRIO
    1.46
    Activations Density 0.008%

    No Known Activations