© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1001
    Prev
    Next
    INDEX
    Explanations

    eicosatetraenoic or popliteal or cerevisiae

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

    scientific taxonomic names and 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_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
     now
    -1.88
     I
    -1.77
     as
    -1.64
    now
    -1.47
     разных
    -1.46
     و
    -1.43
     you
    -1.41
    今も
    -1.41
    èdent
    -1.41
     a
    -1.41
    POSITIVE LOGITS
     '';
    1.79
    ( ̄
    1.64
     when
    1.59
    Jährige
    1.59
     campanha
    1.54
     sufrió
    1.54
     '';
    
    1.52
     [];
    1.50
    !#
    1.48
     because
    1.45
    Activations Density 0.379%

    No Known Activations