© 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-262K
    7. 79979
    Prev
    Next
    INDEX
    Explanations

    traditional concepts and phrases

    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_262k_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
     fazem
    0.55
     простран
    0.52
     careg
    0.50
     относятся
    0.50
     замены
    0.50
     raped
    0.50
     あっ
    0.49
    ﺍ
    0.49
    上で
    0.49
     translocation
    0.49
    POSITIVE LOGITS
    ící
    0.48
     Flor
    0.47
    v
    0.45
    ÿ
    0.45
     house
    0.43
     Monkey
    0.43
     Mond
    0.43
     Monterey
    0.42
    Ari
    0.41
     cuddling
    0.41
    Activations Density 0.003%

    No Known Activations