© 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. 14615
    Prev
    Next
    INDEX
    Explanations

    you are / you're doing

    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
    ensure
    0.54
     ensure
    0.54
     ensuring
    0.53
    Ensure
    0.53
     ensures
    0.51
     memastikan
    0.51
    न्ट
    0.46
    р
    0.43
     ensured
    0.42
     Ensure
    0.42
    POSITIVE LOGITS
     വ്യക്ത
    0.43
    เทพ
    0.41
    用的
    0.40
     yay
    0.39
    หรือ
    0.39
     සම්බන්ධ
    0.38
    騇
    0.38
     භාවිතා
    0.38
     solicitud
    0.38
     Pract
    0.38
    Activations Density 0.003%

    No Known Activations