© 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. 61266
    Prev
    Next
    INDEX
    Explanations

    indicates creativity

    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
    ЕР
    0.38
     впечат
    0.38
    ਾ
    0.38
    е
    0.37
    ཋ
    0.37
    ê
    0.36
    Პ
    0.36
    ג
    0.36
    Მ
    0.36
    Დ
    0.35
    POSITIVE LOGITS
     Philosophy
    0.41
     Para
    0.40
     für
    0.39
     {
    0.39
     para
    0.38
     Allows
    0.37
     Plex
    0.36
     för
    0.36
     Triangle
    0.36
     Music
    0.35
    Activations Density 0.036%

    No Known Activations