© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115191
    Prev
    Next
    INDEX
    Explanations

    unplanned, impulsive, or unaware actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    馋
    0.37
    忌
    0.36
     Dip
    0.35
     Reliability
    0.35
    視
    0.35
    エリア
    0.35
     Areas
    0.34
     discontinue
    0.34
    挚
    0.34
     uncertainty
    0.33
    POSITIVE LOGITS
     unknowingly
    0.62
     unwittingly
    0.53
     forgot
    0.48
     unaware
    0.45
     unintentionally
    0.45
     unsus
    0.44
     forgotten
    0.43
     сразу
    0.42
    Forgot
    0.41
     অন্যায়
    0.40
    Activations Density 0.011%

    No Known Activations