© 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. 85274
    Prev
    Next
    INDEX
    Explanations

    owl, Athena, Minerva

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

    The neuron strongly activates on mentions of owls and their symbolic names (e.g. “owl,” “Owls,” “Athena,” “Minerva”).

    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
     was
    -2.20
    ,"
    -2.03
     capuche
    -1.80
    ",
    -1.78
    
    -1.70
    odeon
    -1.67
     Agrega
    -1.67
     émission
    -1.66
    )"
    -1.66
    ?"
    -1.65
    POSITIVE LOGITS
    ↵↵
    2.09
    </td>
    1.86
     “
    1.77
    </b>
    1.74
     The
    1.60
    _
    1.51
    <i>
    1.45
    1.45
     fach
    1.43
     tzu
    1.42
    Activations Density 0.011%
    No Known Activations