© 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. 56694
    Prev
    Next
    INDEX
    Explanations

    moves again to a new place or version

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

    origin, purpose, existence

    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
    2
    0.47
    8
    0.43
     eighteenth
    0.41
     orci
    0.41
     |
    0.40
    Enviar
    0.40
     commercially
    0.40
     Minutes
    0.40
     Quốc
    0.39
    4
    0.39
    POSITIVE LOGITS
    行星
    0.47
    柰
    0.46
     неско
    0.46
     космо
    0.45
    ీ
    0.45
     Йо
    0.44
     формула
    0.42
    אָ
    0.42
     научно
    0.42
     Бог
    0.41
    Activations Density 0.000%

    No Known Activations