© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9541
    Prev
    Next
    INDEX
    Explanations

    character revelation

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     peasantry
    0.64
    统治
    0.64
     conquest
    0.61
     inhabitants
    0.60
     conquista
    0.60
     anthrop
    0.59
     メンズ
    0.56
    只
    0.56
     lazy
    0.55
     peacetime
    0.55
    POSITIVE LOGITS
     incriminating
    0.83
     sabot
    0.74
     confession
    0.72
     confes
    0.71
     revealing
    0.70
     confess
    0.69
     rivel
    0.66
     revelation
    0.66
     compromising
    0.65
    证据
    0.65
    Activations Density 0.070%

    No Known Activations