© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8840
    Prev
    Next
    INDEX
    Explanations

    Therefore, the answer is

    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
     등의
    0.42
     Wanted
    0.40
     chwil
    0.39
     mewn
    0.39
    ?]
    0.38
    Interesting
    0.38
     puzzling
    0.38
     helpful
    0.37
    0.37
     concludes
    0.37
    POSITIVE LOGITS
    。
    0.59
     എന്നതാണ്
    0.54
    $.}
    0.50
    ''.
    0.49
     причем
    0.48
    其次
    0.48
    ®.
    0.48
     appunto
    0.48
    *.
    0.47
    或者是
    0.47
    Activations Density 0.188%

    No Known Activations