© 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. 2916
    Prev
    Next
    INDEX
    Explanations

    adjusting settings

    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
     manipulate
    0.70
     lasso
    0.64
     bandage
    0.59
     moment
    0.57
     synthesized
    0.57
    ⁹
    0.57
     class
    0.56
     memory
    0.56
    ৯
    0.56
     debug
    0.55
    POSITIVE LOGITS
    is
    1.02
    on
    0.85
    settings
    0.77
    setting
    0.71
    ’
    0.70
    to
    0.70
    preferences
    0.69
    as
    0.68
    Settings
    0.68
    Setting
    0.66
    Activations Density 0.028%

    No Known Activations