© 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. 22-GEMMASCOPE-RES-131K
    7. 27319
    Prev
    Next
    INDEX
    Explanations

    when mentioning entities

    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_22/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
    ところに
    -0.98
    ленность
    -0.95
    ところは
    -0.94
    を超
    -0.92
     zaczyna
    -0.91
     zerstört
    -0.88
     voitures
    -0.86
     réve
    -0.85
    死去
    -0.84
     polega
    -0.84
    POSITIVE LOGITS
     when
    2.58
     who
    2.38
     during
    1.68
     هنگام
    1.59
     cuando
    1.56
     to
    1.53
    ในการ
    1.53
     quando
    1.43
     ketika
    1.40
     whose
    1.38
    Activations Density 0.138%

    No Known Activations