© 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. 53888
    Prev
    Next
    INDEX
    Explanations

    intensive, approximate, super

    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
    urable
    0.50
     itself
    0.50
    atic
    0.48
    ible
    0.47
    ability
    0.47
    advice
    0.44
    atan
    0.43
    }{
    0.43
    ')
    0.43
    aturally
    0.42
    POSITIVE LOGITS
     côte
    0.63
     bakın
    0.47
     Covington
    0.47
     pâte
    0.46
    ﺜ
    0.46
     gått
    0.46
     volg
    0.45
     Ko
    0.45
     Österreich
    0.44
     geomet
    0.44
    Activations Density 0.003%

    No Known Activations