© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11919
    Prev
    Next
    INDEX
    Explanations

    inner self, world, voice, critic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    re
    1.14
    ↵
    1.10
     phd
    0.90
    spider
    0.89
    ransfer
    0.89
    j
    0.87
    谍
    0.87
    Bsky
    0.86
    resistant
    0.84
     tabuleiro
    0.83
    POSITIVE LOGITS
    érrez
    1.07
    깊
    1.05
    շ
    0.97
     وخ
    0.94
    нняя
    0.93
    uración
    0.93
     напряжения
    0.91
    ন্তন
    0.91
    нь
    0.90
     tempData
    0.89
    Activations Density 0.011%

    No Known Activations