© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27509
    Prev
    Next
    INDEX
    Explanations

    scientific species names

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

    scientific names of animal and plant species in taxonomic classifications.

    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
    整天
    -1.19
     zuvor
    -1.18
     unmittelbar
    -1.12
     vọng
    -1.10
    l
    -1.08
    p
    -1.08
     mehreren
    -1.07
    v
    -1.04
    beiten
    -1.03
     passou
    -1.03
    POSITIVE LOGITS
     veldig
    1.32
     vanskelig
    1.25
    بانی
    1.19
     ПОД
    1.18
     spesielt
    1.18
     ИЗ
    1.17
     БО
    1.17
     ПРИ
    1.16
     сахара
    1.15
     mesmas
    1.14
    Activations Density 0.052%

    No Known Activations