© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 76
    Prev
    Next
    INDEX
    Explanations

    figure 1

    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
     the
    -1.78
     by
    -1.67
    },
    -1.55
     other
    -1.53
     другие
    -1.40
     wysokość
    -1.38
     других
    -1.38
     einzelne
    -1.35
    Карьера
    -1.34
     become
    -1.32
    POSITIVE LOGITS
    Ecotoxicity
    1.38
     izvē
    1.24
    続
    1.23
    是在
    1.22
     tege
    1.21
    草莓
    1.20
     animosity
    1.20
     geforce
    1.20
    ALTH
    1.18
     indien
    1.17
    Activations Density 0.151%

    No Known Activations