© 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. 8905
    Prev
    Next
    INDEX
    Explanations

    significant life concepts

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

    abstract concepts and metaphorical phrases, particularly related to powerful emotional or symbolic ideas.

    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
     you
    -1.71
     there
    -1.67
     in
    -1.65
     betekent
    -1.63
     These
    -1.62
     dapatkan
    -1.60
     rijden
    -1.56
     onderhoud
    -1.52
     krijgen
    -1.48
     as
    -1.45
    POSITIVE LOGITS
    úncia
    1.62
    見ても
    1.45
     lagos
    1.45
     duquel
    1.38
     raisonnable
    1.38
    呖
    1.37
     soie
    1.37
     gants
    1.36
    锉
    1.35
    νης
    1.34
    Activations Density 0.089%

    No Known Activations