© 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-262K
    7. 24852
    Prev
    Next
    INDEX
    Explanations

    small size

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     coarsely
    0.50
    粗
    0.46
    惘
    0.41
    Offline
    0.39
    惰
    0.38
    UNION
    0.38
    દાવાદ
    0.38
     kasar
    0.38
    緩
    0.38
    iarism
    0.37
    POSITIVE LOGITS
     small
    2.42
     tiny
    2.33
     smaller
    2.19
    small
    2.17
     diminutive
    2.17
     Small
    2.14
     kecil
    2.14
     pequeño
    2.14
    Small
    2.13
     petite
    2.13
    Activations Density 0.079%

    No Known Activations