© 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. 10-GEMMASCOPE-RES-131K
    7. 10635
    Prev
    Next
    INDEX
    Explanations

    Anopheles, old years

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

    scientific nomenclature and taxonomic identifiers.

    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_10/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
     schaff
    -1.49
     alles
    -1.17
    confined
    -1.16
    ▂
    -1.13
     چیست
    -1.12
    Seven
    -1.12
     Three
    -1.09
     bén
    -1.09
     Two
    -1.08
     angele
    -1.08
    POSITIVE LOGITS
     here
    1.77
     that
    1.32
     to
    1.30
    ൺ
    1.07
    ležité
    1.05
     wiederholt
    1.05
     藤
    1.04
     була
    1.03
     était
    1.02
     нашим
    1.01
    Activations Density 0.198%

    No Known Activations