© 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. 1250
    Prev
    Next
    INDEX
    Explanations

    date and content type indicators

    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
     That
    -2.38
    เกง
    -2.27
     शुर
    -2.23
     que
    -2.23
    …？
    -2.06
    ቷ
    -2.06
    描いた
    -2.05
     \
    -2.00
     MUNDO
    -1.98
    ;
    -1.96
    POSITIVE LOGITS
    al
    2.80
    la
    2.72
    of
    2.66
    1
    2.59
    I
    2.58
    t
    2.52
    en
    2.38
    ce
    2.36
    th
    2.34
    e
    2.31
    Activations Density 0.000%

    No Known Activations