© 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. 28334
    Prev
    Next
    INDEX
    Explanations

    displayed or shown information

    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
    eight
    -1.05
    bihi
    -1.03
    囔
    -1.02
     успешно
    -1.02
     xong
    -0.98
     nötig
    -0.96
     ess
    -0.95
    Redirect
    -0.94
     we
    -0.94
     thì
    -0.93
    POSITIVE LOGITS
     on
    1.76
     displayed
    1.41
     information
    1.38
     appear
    1.31
     your
    1.28
     appears
    1.10
    ленный
    1.09
    foundland
    1.08
     দেখ
    1.06
     their
    1.05
    Activations Density 0.110%

    No Known Activations