© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58123
    Prev
    Next
    INDEX
    Explanations

    squirrels and squirrel monkeys

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

    The neuron identifies the word "squirrel" and variations like "squirrels," with higher activation for the complete word and lower activation for partial forms.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    Negative Logits
    蠵
    -2.84
    </b>
    -2.58
    抔
    -2.50
    晙
    -2.50
    ஂ
    -2.45
     razões
    -2.39
    缡
    -2.33
    攰
    -2.31
    摃
    -2.31
    örté
    -2.30
    POSITIVE LOGITS
    </h3>
    3.08
    ;
    2.94
    <bos>
    2.61
    '
    2.58
     utilizing
    2.36
    U
    2.19
     utilising
    2.17
    釭
    2.16
    
    2.16
     ſte
    2.08
    Activations Density 0.007%

    No Known Activations