© 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. 16-GEMMASCOPE-2-RES-262K
    7. 49941
    Prev
    Next
    INDEX
    Explanations

    regime, metrics, long, tongue

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Кре
    0.53
     alluvial
    0.52
     የመ
    0.50
    definition
    0.50
     చూప
    0.50
    Controlled
    0.50
    Definition
    0.49
    StillWater
    0.49
    浧
    0.47
    ForSettings
    0.47
    POSITIVE LOGITS
    ژ
    0.52
    ।
    0.50
    。
    0.46
     postcard
    0.44
     fatto
    0.43
    ﻜ
    0.43
     childhood
    0.43
     causa
    0.42
     banner
    0.42
    克
    0.42
    Activations Density 0.000%

    No Known Activations