© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21512
    Prev
    Next
    INDEX
    Explanations

    numbers with plus-minus

    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
     This
    -2.72
     Usually
    -2.28
     Before
    -2.25
    0
    -2.23
     手作り
    -2.23
     Often
    -2.17
    ”(
    -2.16
    食べる
    -2.11
    Probably
    -2.09
     Shortly
    -2.08
    POSITIVE LOGITS
    ￪
    2.64
    坶
    2.52
    ㉕
    2.34
     startling
    2.34
     crappy
    2.31
    狨
    2.30
    蹰
    2.25
     sytu
    2.20
     deſt
    2.19
    賔
    2.19
    Activations Density 0.006%

    No Known Activations