© 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. 13514
    Prev
    Next
    INDEX
    Explanations

    the [purpose/role/context/nuance]

    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
    当前的
    0.41
    那些
    0.39
     totality
    0.39
     mencionado
    0.39
     gradual
    0.38
     its
    0.38
     aforementioned
    0.38
    自己的
    0.37
     в
    0.37
     the
    0.37
    POSITIVE LOGITS
     způ
    0.36
    Textbox
    0.34
    wechsl
    0.34
    <0x93>
    0.34
     États
    0.33
    dois
    0.33
     मोन
    0.33
    with
    0.32
     Voir
    0.32
     Ayrıca
    0.31
    Activations Density 0.142%

    No Known Activations