© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48789
    Prev
    Next
    INDEX
    Explanations

    Australian Eastern Standard Time

    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_40_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
    (-
    0.52
     (-
    0.51
     [-
    0.44
    secondary
    0.41
    색
    0.41
     нега
    0.41
     PRES
    0.40
     cổ
    0.40
    =-
    0.40
     GO
    0.39
    POSITIVE LOGITS
     восто
    0.58
     Восто
    0.49
     eastern
    0.47
    Eastern
    0.46
     Eastern
    0.44
     east
    0.43
    eastern
    0.42
     Tasmania
    0.41
     ईस्ट
    0.40
    澳大利
    0.40
    Activations Density 0.001%

    No Known Activations