© 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. 62176
    Prev
    Next
    INDEX
    Explanations

    whether you

    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
     cả
    0.52
    任何
    0.48
     cualquier
    0.45
     любых
    0.45
    Ո
    0.45
     både
    0.44
     inté
    0.43
     quiser
    0.42
     handyman
    0.42
    वाय
    0.42
    POSITIVE LOGITS
     년
    0.48
     zaradi
    0.42
     ابتدا
    0.40
     благодаря
    0.39
     때문
    0.38
     зазна
    0.38
     zbog
    0.37
    resulting
    0.37
     ४
    0.37
     학
    0.37
    Activations Density 0.040%

    No Known Activations