© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11361
    Prev
    Next
    INDEX
    Explanations

    events

    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
    insular
    0.45
     insulators
    0.44
     insulating
    0.42
    醎
    0.41
    リート
    0.40
     curvil
    0.40
    頑
    0.38
    ardino
    0.38
     microcosm
    0.38
    褛
    0.37
    POSITIVE LOGITS
     events
    0.87
     evento
    0.84
     eventos
    0.82
     événements
    0.81
    事件
    0.80
     собы
    0.80
     arrival
    0.78
     события
    0.77
    ChangeEvent
    0.73
    events
    0.73
    Activations Density 0.042%

    No Known Activations