© 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. 10-GEMMASCOPE-RES-131K
    7. 61503
    Prev
    Next
    INDEX
    Explanations

    biological suffixes and context

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

    scientific and technical terms, particularly chemical compounds and specialized nomenclature.

    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
     with
    -1.66
     your
    -1.59
    歳の
    -1.58
     all
    -1.53
     as
    -1.53
     it
    -1.45
    我的
    -1.45
     tjän
    -1.43
    私の
    -1.41
     úgy
    -1.41
    POSITIVE LOGITS
     to
    1.70
    倹
    1.39
    之助
    1.38
     Qualquer
    1.34
    当事
    1.33
    があれば
    1.31
    寰
    1.28
     اگه
    1.28
    onyme
    1.27
     hybride
    1.26
    Activations Density 0.322%

    No Known Activations