© 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-262K
    7. 204815
    Prev
    Next
    INDEX
    Explanations

    stylized illustration

    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_262k_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
     ریاضی
    0.56
    MinIntensity
    0.54
    𝓌
    0.52
    をした
    0.52
     နှစ်
    0.51
     دوسری
    0.51
    ட்சய
    0.51
    𝘢
    0.51
    墺
    0.50
     Monochrome
    0.50
    POSITIVE LOGITS
    U
    0.52
    0.52
    B
    0.51
    L
    0.48
      
    0.47
     April
    0.47
    P
    0.47
     has
    0.47
     (
    0.46
     is
    0.46
    Activations Density 0.003%

    No Known Activations