© 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. 41-GEMMASCOPE-2-RES-262K
    7. 377
    Prev
    Next
    INDEX
    Explanations

    SQL schema elements

    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_all/layer_41_width_262k_l0_big
    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
     secretions
    0.64
     perfused
    0.60
     température
    0.59
    <unused2168>
    0.58
    <unused973>
    0.56
     vesicles
    0.55
     radiographic
    0.55
     birefring
    0.55
     analyte
    0.55
    閾
    0.55
    POSITIVE LOGITS
     Constraints
    1.00
     Primary
    0.88
     Foreign
    0.87
     Constraint
    0.83
     constraint
    0.82
     Unique
    0.82
    Primary
    0.80
    Unique
    0.80
     Indexes
    0.80
     FK
    0.79
    Activations Density 0.012%

    No Known Activations