© 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. 56368
    Prev
    Next
    INDEX
    Explanations

    building structures or essential information

    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
    A
    0.57
    E
    0.57
    set
    0.57
    T
    0.57
    list
    0.56
    check
    0.56
    size
    0.55
    t
    0.54
    that
    0.53
    S
    0.52
    POSITIVE LOGITS
     spont
    0.49
     Elektrokhimiya
    0.49
    چین
    0.49
     espont
    0.48
    頨
    0.47
     justru
    0.47
     agama
    0.47
    糹
    0.47
     بسیار
    0.46
     cámara
    0.46
    Activations Density 0.012%

    No Known Activations