© 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. 135213
    Prev
    Next
    INDEX
    Explanations

    various technical terms

    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
    Negative Logits
    Workflow
    0.44
    לו
    0.42
    aio
    0.40
     информацией
    0.40
    نر
    0.38
     желательно
    0.38
     Bride
    0.38
    ｴ
    0.38
     சிர
    0.37
    什么的
    0.37
    POSITIVE LOGITS
     utilisés
    0.52
     utilisées
    0.52
     utilizados
    0.44
     মজুম
    0.42
    дық
    0.41
    熹
    0.41
    時点で
    0.41
     utilizzati
    0.40
     Assemblies
    0.40
     CHEMISTRY
    0.40
    Activations Density 0.145%

    No Known Activations