© 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. 40-GEMMASCOPE-2-RES-262K
    7. 215632
    Prev
    Next
    INDEX
    Explanations

    bought both / extremely hard

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    臨
    0.45
     matrice
    0.40
     stal
    0.40
     avvi
    0.40
    ⎙
    0.39
    лейбол
    0.38
     nub
    0.37
    риш
    0.37
    互
    0.37
     linux
    0.37
    POSITIVE LOGITS
    ங்கோ
    0.39
     อำ
    0.39
    рная
    0.39
     слід
    0.38
    onden
    0.37
     Correspondent
    0.36
     Axi
    0.36
    jit
    0.36
    τή
    0.36
     Guarantee
    0.36
    Activations Density 0.000%

    No Known Activations