© 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-65K
    7. 56239
    Prev
    Next
    INDEX
    Explanations

    whisper stories, secrets, opinions

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    깡
    0.39
    !</
    0.37
    λικό
    0.37
    任意
    0.37
     화면
    0.36
    andom
    0.36
     বর্বর
    0.36
    礙
    0.36
    /</
    0.36
     Cowan
    0.36
    POSITIVE LOGITS
     whisper
    1.56
     whispering
    1.46
     whispered
    1.44
     whispers
    1.34
    whis
    1.30
    Whis
    1.28
     Whisper
    1.23
     Whis
    1.12
     murmur
    0.98
     murm
    0.95
    Activations Density 0.038%

    No Known Activations