© 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. 22-GEMMASCOPE-RES-131K
    7. 127957
    Prev
    Next
    INDEX
    Explanations

    animal genus prefixes

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

    scientific genus names of organisms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     your
    -1.47
     will
    -1.41
     you
    -1.41
    ඟ
    -1.35
     on
    -1.34
    Купить
    -1.29
     out
    -1.29
     even
    -1.27
     after
    -1.26
     bagus
    -1.22
    POSITIVE LOGITS
    albeit
    1.64
     zustand
    1.23
    “…
    1.23
     bekym
    1.22
    several
    1.22
     imponer
    1.21
     instruções
    1.19
    在这里
    1.19
    を変更
    1.19
    ⅽ
    1.16
    Activations Density 0.082%

    No Known Activations