© 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. 65052
    Prev
    Next
    INDEX
    Explanations

    one, a, and before nouns

    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_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
     beide
    -1.34
    cais
    -1.15
    inture
    -1.11
     noastră
    -1.07
     Kecamatan
    -1.07
    astră
    -1.07
    oceros
    -1.06
     таком
    -1.06
     zarówno
    -1.06
    uttore
    -1.05
    POSITIVE LOGITS
     all
    1.41
     by
    1.32
     they
    1.20
     who
    1.16
     of
    1.16
     other
    1.14
     on
    1.11
     semua
    1.11
     a
    1.11
    による
    1.09
    Activations Density 0.185%

    No Known Activations