© 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. 15246
    Prev
    Next
    INDEX
    Explanations

    family members and their relationships

    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
    ஊ
    -1.17
     pracuje
    -0.99
    producción
    -0.97
    ludes
    -0.96
    bės
    -0.96
    ducers
    -0.92
     jesteśmy
    -0.90
    地说道
    -0.90
     basé
    -0.89
    camisetas
    -0.89
    POSITIVE LOGITS
     legacy
    1.39
    legacy
    1.10
     by
    1.05
     (†
    1.02
     продолжает
    0.96
     still
    0.93
     leftovers
    0.93
     leftover
    0.93
     गए
    0.88
     Erbe
    0.88
    Activations Density 0.054%

    No Known Activations