© 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. 56109
    Prev
    Next
    INDEX
    Explanations

    cre(a)st, cre(at)inine, cre(ep)

    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
     GRAM
    0.44
     متابعي
    0.43
     JULY
    0.41
     Raza
    0.41
     Synonym
    0.40
     Penta
    0.39
    m
    0.39
    !”.
    0.38
    lush
    0.38
     SOFT
    0.38
    POSITIVE LOGITS
     cre
    0.58
     creș
    0.45
    Cre
    0.44
     springs
    0.44
     кре
    0.43
    ograph
    0.43
     kre
    0.42
     Кре
    0.42
    クレ
    0.42
     creed
    0.42
    Activations Density 0.014%

    No Known Activations