© 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. 84277
    Prev
    Next
    INDEX
    Explanations

    is a

    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
     have
    -1.96
     on
    -1.95
     To
    -1.93
     started
    -1.91
     then
    -1.87
     begin
    -1.86
    1
    -1.84
     can
    -1.81
     and
    -1.81
     always
    -1.79
    POSITIVE LOGITS
     rajut
    2.59
     saveiro
    2.25
     kalender
    2.25
     auffi
    2.23
     estadounid
    2.20
     zoude
    2.20
     vixion
    2.19
     camiset
    2.16
     összefoglaló
    2.16
     唯美
    2.14
    Activations Density 0.067%

    No Known Activations