© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42908
    Prev
    Next
    INDEX
    Explanations

    Medical/business/technical contexts

    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_31_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
    एको
    0.48
    وها
    0.48
    Weak
    0.47
    Quién
    0.47
    蝣
    0.47
    Platforms
    0.46
     İslam
    0.46
    剻
    0.46
    Things
    0.46
    ارهای
    0.46
    POSITIVE LOGITS
     duplex
    0.50
     augmenting
    0.48
     metastatic
    0.48
     branching
    0.47
     micrographs
    0.46
     augment
    0.46
     multiplex
    0.46
     prolifer
    0.46
     considerate
    0.46
     proliferate
    0.46
    Activations Density 0.001%

    No Known Activations