© 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. 3058
    Prev
    Next
    INDEX
    Explanations

    remembering instructions or warnings

    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
     repulsive
    0.52
     sunflower
    0.51
     fibroblast
    0.49
     decolor
    0.48
    '
    0.48
     furtherance
    0.48
     sulfide
    0.47
     ним
    0.47
     অনে
    0.47
     inconsist
    0.46
    POSITIVE LOGITS
    Remember
    0.78
    remember
    0.77
     remember
    0.76
     Remember
    0.75
     помнить
    0.63
    า
    0.62
    记得
    0.61
     remembers
    0.59
     recuerda
    0.59
     pamię
    0.59
    Activations Density 0.038%

    No Known Activations