© 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. 35784
    Prev
    Next
    INDEX
    Explanations

    steering column and posts

    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
     l
    0.67
     can
    0.62
     (
    0.58
    して
    0.58
     =
    0.58
    々は
    0.58
    ুস
    0.56
    Six
    0.56
     NES
    0.56
    いた
    0.54
    POSITIVE LOGITS
    疟
    0.64
     théorie
    0.63
     entrenamiento
    0.63
     conectar
    0.61
    drž
    0.61
    тека
    0.61
    пси
    0.59
     velocidades
    0.59
    نا
    0.59
     déficit
    0.59
    Activations Density 0.000%

    No Known Activations