© 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. 41508
    Prev
    Next
    INDEX
    Explanations

    we have a scenario

    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
     you
    -1.55
     można
    -1.31
     [
    -1.23
    end
    -1.23
     its
    -1.15
     could
    -1.12
     would
    -1.11
    ACKNOWLEDGMENT
    -1.11
     will
    -1.09
    }
    -1.07
    POSITIVE LOGITS
     that
    1.53
    Љ
    1.27
    десь
    1.25
    Тарих
    1.20
    ఈ
    1.19
    люми
    1.18
    интере
    1.16
    Finalmente
    1.15
     with
    1.14
    alians
    1.13
    Activations Density 0.187%

    No Known Activations