© 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-16K
    7. 6679
    Prev
    Next
    INDEX
    Explanations

    describing actions, states, or roles

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    et
    0.62
    s
    0.59
    0
    0.59
    1
    0.58
    ad
    0.53
    a
    0.49
     the
    0.48
    c
    0.47
    o
    0.47
     *
    0.46
    POSITIVE LOGITS
     magnificence
    0.61
     استعمال
    0.55
     efectuar
    0.55
     supposition
    0.54
     splendid
    0.54
     ordinairement
    0.53
    한테
    0.52
     чтоб
    0.51
     asimismo
    0.51
     multitudes
    0.50
    Activations Density 0.146%

    No Known Activations