© 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. 31-GEMMASCOPE-2-RES-262K
    7. 200145
    Prev
    Next
    INDEX
    Explanations

    jetting, props, supporting, potential, roofs, FTP

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Pé
    0.54
    ujú
    0.51
     Pia
    0.49
     Pele
    0.49
    rame
    0.49
    っいて
    0.48
    参见
    0.48
     Ranj
    0.47
    入門
    0.47
    飙
    0.47
    POSITIVE LOGITS
    downs
    0.46
    dit
    0.44
    tyw
    0.43
    DOWN
    0.41
    রির
    0.41
    –
    0.41
    down
    0.41
    OL
    0.40
    dirs
    0.40
    but
    0.40
    Activations Density 0.003%

    No Known Activations