© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21784
    Prev
    Next
    INDEX
    Explanations

    RunwayML

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;")
    0.42
    일
    0.41
     problematic
    0.40
     subsequent
    0.39
    !')
    0.38
     incompar
    0.38
     thoughtful
    0.37
     intellectual
    0.36
     questionable
    0.36
     essentially
    0.36
    POSITIVE LOGITS
     RUN
    0.63
     Run
    0.61
    RUN
    0.55
    Run
    0.52
     रन
    0.51
     Runner
    0.49
    🏃
    0.48
     Runners
    0.46
     перево
    0.45
     chạy
    0.44
    Activations Density 0.006%

    No Known Activations