© 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. 4832
    Prev
    Next
    INDEX
    Explanations

    isn't, doesn't

    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
     for
    1.61
    6
    1.05
    4
    1.05
    3
    1.03
    8
    1.03
    for
    1.01
    9
    0.96
    7
    0.92
    ف
    0.90
    К
    0.89
    POSITIVE LOGITS
    ер
    0.69
    した
    0.67
     is
    0.66
    _
    0.66
    การ
    0.64
    ва
    0.63
    ने
    0.59
    ет
    0.59
    ள்
    0.59
    ને
    0.58
    Activations Density 0.444%

    No Known Activations