© 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. 53-GEMMASCOPE-2-RES-262K
    7. 50310
    Prev
    Next
    INDEX
    Explanations

    graphical programming

    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_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     NOMBRE
    0.45
     სას
    0.42
    ᐟ
    0.40
     చి
    0.39
     infrastructural
    0.39
     bü
    0.37
     미술
    0.37
    RTT
    0.37
     অগ্র
    0.36
    OSO
    0.36
    POSITIVE LOGITS
    ួល
    0.38
     Accuracy
    0.38
     accurate
    0.37
     Accurate
    0.36
     스테
    0.36
     accuracy
    0.35
    Pu
    0.35
    
    0.35
    "],
    0.35
    accuracy
    0.35
    Activations Density 0.001%

    No Known Activations