© 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. 16-GEMMASCOPE-2-RES-262K
    7. 12848
    Prev
    Next
    INDEX
    Explanations

    connections between words

    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_16_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
    in
    1.18
    er
    1.01
    u
    0.89
    as
    0.77
    o
    0.75
    ba
    0.71
    al
    0.69
    key
    0.68
    ak
    0.67
    ana
    0.66
    POSITIVE LOGITS
     robbers
    0.59
    ﺎ
    0.57
     nhau
    0.57
     А
    0.56
     തമ്മ
    0.53
     hypersurfaces
    0.53
    его
    0.53
    ного
    0.52
     equilateral
    0.52
     thermoplastics
    0.52
    Activations Density 0.100%

    No Known Activations