© 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. 84748
    Prev
    Next
    INDEX
    Explanations

    Jared, loaf, loafers, loath

    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
     notwendigen
    -2.72
     greateſt
    -2.61
    Ꮷ
    -2.56
    鲧
    -2.52
    vantaged
    -2.48
     technischen
    -2.39
    ︕
    -2.38
    淠
    -2.38
    CHREIB
    -2.36
     ส์
    -2.36
    POSITIVE LOGITS
     '
    2.80
    --
    2.58
    {
    2.44
    姥
    2.42
     t
    2.39
    ,
    2.39
    s
    2.34
    +
    2.27
     be
    2.23
    as
    2.17
    Activations Density 0.002%

    No Known Activations