© 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. 1037
    Prev
    Next
    INDEX
    Explanations

    the word cat

    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
     ส์
    -2.42
    𖧵
    -2.25
    惴
    -2.23
    égio
    -2.22
    ឵
    -2.22
     pozor
    -2.19
    媄
    -2.17
     textu
    -2.13
    糌
    -2.13
    eſ
    -2.06
    POSITIVE LOGITS
    '
    3.05
    y
    2.75
    s
    2.69
    ’
    2.58
    D
    2.50
    4
    2.38
    ?
    2.27
    "
    2.25
    cat
    2.19
    k
    2.16
    Activations Density 0.004%

    No Known Activations