© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 111454
    Prev
    Next
    INDEX
    Explanations

    explanations and definitions

    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
     Qué
    0.65
     Quebec
    0.64
     Québec
    0.64
     Prancis
    0.60
     França
    0.59
     Maroc
    0.59
     Montreal
    0.56
     É
    0.56
     qué
    0.55
     Montréal
    0.54
    POSITIVE LOGITS
    PIO
    0.42
     যেই
    0.41
    Stokes
    0.40
    FLOAT
    0.39
     stocked
    0.38
     rattled
    0.37
    blown
    0.37
     વખ
    0.37
    ioon
    0.36
    টিআই
    0.36
    Activations Density 0.020%

    No Known Activations