© 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. 14652
    Prev
    Next
    INDEX
    Explanations

    accomplishments and quantities

    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
     किंवा
    0.47
     arba
    0.45
    又は
    0.44
     अथवा
    0.43
     அல்லது
    0.43
    或者是
    0.43
    웨
    0.43
     Вален
    0.42
    または
    0.42
     പതി
    0.42
    POSITIVE LOGITS
     lograron
    0.50
     avevano
    0.48
    a
    0.46
    居然
    0.45
     logros
    0.45
     étaient
    0.45
     hatte
    0.44
     astonished
    0.44
     damals
    0.44
     était
    0.44
    Activations Density 0.020%

    No Known Activations