© 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. 18989
    Prev
    Next
    INDEX
    Explanations

    parrot and Polly

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

    The neuron selectively activates on tokens naming or referring to parrots (common names and taxonomic terms).

    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
    จริงๆ
    -2.14
    </strong>
    -2.14
    ?"
    -2.02
     \
    -2.02
    共有
    -2.00
     snug
    -1.93
    Pendidikan
    -1.92
    排行榜
    -1.91
     genius
    -1.91
     його
    -1.88
    POSITIVE LOGITS
    </td>
    3.56
    }
    2.72
    2.52
    鹉
    2.47
    ;
    2.17
    ’).
    2.11
     creó
    2.06
     pai
    2.06
    ’，
    1.98
    铩
    1.95
    Activations Density 0.004%

    No Known Activations