© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51955
    Prev
    Next
    INDEX
    Explanations

    without reporting, programming, or changes

    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_65k_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
     nicht
    0.48
     as
    0.47
     valamint
    0.45
     not
    0.45
     ámbito
    0.44
     and
    0.44
    而不是
    0.43
    ｾ
    0.43
    icrosoft
    0.42
     lieu
    0.42
    POSITIVE LOGITS
    แรก
    0.48
     먼저
    0.47
     ಗಮನ
    0.47
     предвари
    0.46
     siquiera
    0.46
    Divid
    0.45
    Intermediate
    0.45
    Dedicated
    0.45
     ആദ്യം
    0.45
     eerst
    0.44
    Activations Density 0.088%

    No Known Activations