© 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. 102814
    Prev
    Next
    INDEX
    Explanations

    initial outlay

    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
    kanı
    -1.44
     lorsqu
    -1.36
    KommentareTeilen
    -1.35
     when
    -1.28
    ในการ
    -1.27
     ২০
    -1.24
    ƍ
    -1.21
    鹃
    -1.21
     WHEN
    -1.20
    dolu
    -1.20
    POSITIVE LOGITS
     one
    1.50
     atentos
    1.18
    decoración
    1.05
    ↵
    1.02
     samma
    0.99
     mismas
    0.97
     одного
    0.96
     traduction
    0.96
    ✁
    0.96
    🧩
    0.96
    Activations Density 0.042%

    No Known Activations