© 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. 34-GEMMASCOPE-RES-131K
    7. 83659
    Prev
    Next
    INDEX
    Explanations

    existence or quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     it
    -1.60
    一个
    -1.38
    一個
    -1.15
    它
    -1.14
     advice
    -1.13
    it
    -1.12
     STUFF
    -1.11
     imagery
    -1.09
    нами
    -1.08
     footage
    -1.07
    POSITIVE LOGITS
     fewer
    1.87
     few
    1.84
     some
    1.84
     plenty
    1.83
     no
    1.80
     two
    1.80
     several
    1.71
     also
    1.66
     lots
    1.55
     many
    1.49
    Activations Density 0.049%

    No Known Activations