© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38642
    Prev
    Next
    INDEX
    Explanations

    Service by Design

    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_34/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
     pembe
    -0.81
     potencia
    -0.72
     H
    -0.71
     комплект
    -0.70
    bouncy
    -0.68
     hasilnya
    -0.68
     pursuant
    -0.68
     surprise
    -0.67
     fugitive
    -0.66
     C
    -0.66
    POSITIVE LOGITS
     Emirates
    0.92
     Breit
    0.90
    ==="
    0.88
    KOV
    0.87
     broma
    0.86
     consequ
    0.86
     EXPO
    0.86
    olisme
    0.84
     NIK
    0.82
    ENSIS
    0.82
    Activations Density 0.011%

    No Known Activations