© 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. 40-GEMMASCOPE-2-RES-262K
    7. 3098
    Prev
    Next
    INDEX
    Explanations

    setting app or model titles

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    观众
    0.45
     aquele
    0.45
    ړ
    0.45
    ாட்டு
    0.44
     пройти
    0.43
     equalize
    0.42
    бург
    0.42
     ጥላ
    0.42
     важно
    0.42
     понять
    0.41
    POSITIVE LOGITS
    the
    0.42
    luc
    0.41
     shelter
    0.39
     I
    0.38
    0.38
    ten
    0.38
     Luc
    0.38
     mutations
    0.38
    ts
    0.37
     Shelter
    0.37
    Activations Density 0.000%

    No Known Activations