© 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. 10-GEMMASCOPE-RES-131K
    7. 42913
    Prev
    Next
    INDEX
    Explanations

    contrast conjunctions

    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
    商品説明
    -1.55
     anledning
    -1.37
     egenskaper
    -1.35
    }
    -1.35
     tempera
    -1.31
     berbasis
    -1.30
     mengerti
    -1.30
     bygger
    -1.30
     दोनों
    -1.30
     vienas
    -1.29
    POSITIVE LOGITS
    .
    1.54
     which
    1.43
    へ向
    1.41
     were
    1.38
    ⟣
    1.36
    苼
    1.34
    Ꮸ
    1.32
     couldn
    1.29
     какво
    1.29
     who
    1.28
    Activations Density 0.091%

    No Known Activations