© 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. 22-GEMMASCOPE-RES-131K
    7. 36415
    Prev
    Next
    INDEX
    Explanations

    information reproducing apparatus

    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_22/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
     people
    -1.94
     only
    -1.81
     when
    -1.80
     because
    -1.78
     for
    -1.77
     three
    -1.73
     other
    -1.70
     some
    -1.69
     several
    -1.63
     more
    -1.63
    POSITIVE LOGITS
    rdoba
    1.47
    oped
    1.44
     pittores
    1.41
     Dinas
    1.41
     لذا
    1.35
    whats
    1.34
     insanely
    1.34
     luscious
    1.30
    EVEN
    1.30
     secrétaire
    1.30
    Activations Density 0.000%

    No Known Activations