© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111483
    Prev
    Next
    INDEX
    Explanations

    important role

    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
     něj
    -1.73
    ᾷ
    -1.72
     lèvres
    -1.71
    licopter
    -1.63
    鸲
    -1.59
    过敏
    -1.56
    鵟
    -1.53
     廠
    -1.53
     berkomunikasi
    -1.50
    igth
    -1.49
    POSITIVE LOGITS
     you
    2.03
     of
    1.80
     in
    1.71
     then
    1.70
     so
    1.68
     we
    1.67
     create
    1.64
     there
    1.63
     other
    1.63
     that
    1.55
    Activations Density 0.224%

    No Known Activations