© 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. 62132
    Prev
    Next
    INDEX
    Explanations

    explaining, showcase, used, with

    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
     alumin
    0.53
     changer
    0.51
     공동
    0.50
     positif
    0.49
    commend
    0.48
     ಔ
    0.47
     minhas
    0.47
     coeff
    0.47
     cumplir
    0.46
    paramet
    0.46
    POSITIVE LOGITS
    იმ
    0.47
    ing
    0.47
     unsightly
    0.44
    ة
    0.43
    it
    0.43
    ي
    0.43
     Cur
    0.43
    when
    0.43
     Due
    0.43
     springing
    0.42
    Activations Density 0.001%

    No Known Activations