© 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. 22-GEMMASCOPE-RES-131K
    7. 13472
    Prev
    Next
    INDEX
    Explanations

    scientific species names suffixes

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

    Latin taxonomic species names, especially endings like 'ata', 'ensis', and 'is'.

    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
    P
    -1.61
    L
    -1.52
    J
    -1.49
    C
    -1.43
    --
    -1.40
    F
    -1.40
    H
    -1.37
    T
    -1.34
    ing
    -1.34
    N
    -1.34
    POSITIVE LOGITS
    Zubereitung
    1.65
     bambou
    1.55
    joje
    1.48
     sés
    1.47
     miroir
    1.44
     bekym
    1.42
     öv
    1.42
    dienne
    1.41
    hares
    1.40
     cadeau
    1.39
    Activations Density 0.023%

    No Known Activations