© 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. 31660
    Prev
    Next
    INDEX
    Explanations

    presentation, urgent, goodness

    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
    纪
    0.43
     అనేది
    0.42
    τικ
    0.42
     அதிகார
    0.42
    蜈
    0.40
    এটা
    0.40
     unsustainable
    0.39
    한다는
    0.38
    하려면
    0.38
     افر
    0.38
    POSITIVE LOGITS
    -]
    0.46
    ición
    0.45
     uitge
    0.44
     обосно
    0.43
    or
    0.41
    ismo
    0.40
    fig
    0.39
     declaración
    0.39
    IDADES
    0.39
    id
    0.39
    Activations Density 0.002%

    No Known Activations