© 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. 119923
    Prev
    Next
    INDEX
    Explanations

    not followed by verb

    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
    挹
    -1.61
     coû
    -1.59
    ogical
    -1.55
     sembler
    -1.52
    zembro
    -1.49
    ledad
    -1.48
    gradable
    -1.48
    antry
    -1.45
     that
    -1.44
     liet
    -1.43
    POSITIVE LOGITS
     you
    1.57
     two
    1.41
     just
    1.39
     Frases
    1.39
     from
    1.37
     вони
    1.34
     four
    1.32
     можна
    1.29
     Saúde
    1.27
     as
    1.25
    Activations Density 0.023%

    No Known Activations