© 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. 204439
    Prev
    Next
    INDEX
    Explanations

    aurorae and lights

    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
     را
    0.49
     ਚ
    0.47
     مغ
    0.47
     возра
    0.46
     डबल
    0.46
     می‌توانید
    0.46
     حا
    0.45
     dissociate
    0.45
    ።
    0.44
    FirstFit
    0.44
    POSITIVE LOGITS
     Tips
    0.46
     Tail
    0.45
     tails
    0.44
     Points
    0.43
     uneven
    0.43
     mạnh
    0.43
    驟
    0.43
     sprawling
    0.42
    티브
    0.42
     Orientation
    0.42
    Activations Density 0.000%

    No Known Activations