© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56423
    Prev
    Next
    INDEX
    Explanations

    numbers after words or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    assess plants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     perverse
    0.46
    ారీ
    0.45
     personalise
    0.43
    之际
    0.43
    Repartition
    0.40
    ែ
    0.40
    帷
    0.40
    旨在
    0.40
    建设项目
    0.39
    会对
    0.39
    POSITIVE LOGITS
    ]))
    0.56
    łączy
    0.55
    cvec
    0.53
     スター
    0.51
     Кам
    0.50
    ]['
    0.48
    উপর
    0.47
     നാല
    0.47
     দী
    0.47
    sten
    0.46
    Activations Density 0.000%

    No Known Activations