© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 44870
    Prev
    Next
    INDEX
    Explanations

    lights followed by tastefully

    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
    Negative Logits
     on
    0.54
     which
    0.49
    ,
    0.49
     influencing
    0.46
     due
    0.45
     collars
    0.44
     being
    0.44
     influence
    0.44
     over
    0.43
    ую
    0.43
    POSITIVE LOGITS
    软件包
    0.55
     숫자
    0.52
     숫
    0.52
    Setelah
    0.51
    Dopo
    0.50
    apadani
    0.49
    analisi
    0.48
    ismillah
    0.48
     secolo
    0.48
     ሶ
    0.47
    Activations Density 0.007%

    No Known Activations