© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180943
    Prev
    Next
    INDEX
    Explanations

    geographic locations and educational tasks

    np_acts-logits-general · gemini-2.5-flash-lite

    shapes and motherly figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    १८४
    0.51
     antibodies
    0.49
    ڎ
    0.49
    বোধ
    0.48
    ofield
    0.48
     Combs
    0.47
     Antibodies
    0.47
    prior
    0.47
     IncludeField
    0.46
     اولین
    0.45
    POSITIVE LOGITS
    <0xE3>
    0.49
     AZ
    0.43
    Azur
    0.42
    లె
    0.42
     USU
    0.42
     niz
    0.41
     phenomen
    0.41
    可能です
    0.40
    纷纷
    0.40
    為
    0.40
    Activations Density 0.001%

    No Known Activations