© 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. 22-GEMMASCOPE-RES-131K
    7. 65102
    Prev
    Next
    INDEX
    Explanations

    simplify, evaluate, or calculate expressions

    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
     model
    -0.98
    unción
    -0.98
    וּ
    -0.95
    እ
    -0.93
     только
    -0.92
     berguna
    -0.92
    назна
    -0.91
    urige
    -0.91
     detención
    -0.91
     variétés
    -0.90
    POSITIVE LOGITS
    ื่อง
    1.21
    rosia
    1.06
     geprek
    1.05
    𝚊
    1.02
     poliuret
    1.00
     multicolore
    1.00
    ଼
    1.00
    зию
    0.96
    راعة
    0.96
     isolado
    0.96
    Activations Density 0.060%

    No Known Activations