© 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. 40520
    Prev
    Next
    INDEX
    Explanations

    person names

    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
    ↵↵
    -3.17
     we
    -2.84
     but
    -2.45
     o
    -2.38
     You
    -2.36
     beinahe
    -2.36
     of
    -2.25
     意思
    -2.23
    中でも
    -2.22
    茴
    -2.22
    POSITIVE LOGITS
     内衣
    3.45
    0
    3.38
    which
    3.02
     consegui
    2.81
    Ꮠ
    2.78
    糴
    2.78
    鐃
    2.77
    if
    2.77
     материалы
    2.69
     tiveram
    2.64
    Activations Density 0.006%

    No Known Activations