© 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. 55934
    Prev
    Next
    INDEX
    Explanations

    broader reach, more secure

    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
    ENAME
    0.46
     apariencia
    0.46
     analogs
    0.45
    mts
    0.45
     amphibians
    0.45
     nomenclatura
    0.45
    A
    0.44
    uem
    0.43
    ITES
    0.43
     groups
    0.42
    POSITIVE LOGITS
    เพื่อ
    0.53
    剧情
    0.49
     เพื่อ
    0.48
     לש
    0.47
     Архивная
    0.46
     новой
    0.46
    在该
    0.46
     chez
    0.46
    ไว้
    0.45
    愆
    0.45
    Activations Density 0.008%

    No Known Activations