© 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. 34-GEMMASCOPE-RES-131K
    7. 56856
    Prev
    Next
    INDEX
    Explanations

    fungal and plant scientific names

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

    names of fungi and scientific taxonomic classifications.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ערך
    -0.75
     Green
    -0.72
    屍
    -0.71
     TextEditing
    -0.70
     Feld
    -0.69
    probleme
    -0.69
    ետ
    -0.69
     Fang
    -0.69
    raisemb
    -0.69
     Fowler
    -0.68
    POSITIVE LOGITS
     socioeconomic
    0.82
     Montagne
    0.75
     dennoch
    0.73
     Thore
    0.73
     carbón
    0.72
    Coo
    0.71
    办事
    0.71
     خواست
    0.71
    SenderId
    0.70
     deceptive
    0.69
    Activations Density 0.057%

    No Known Activations