© 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. 40782
    Prev
    Next
    INDEX
    Explanations

    criminal mastermind

    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
     colour
    0.43
     iceberg
    0.43
     Mind
    0.41
     minds
    0.41
    區域
    0.41
     islamic
    0.40
     Prince
    0.40
     OECD
    0.39
    g
    0.39
     realist
    0.39
    POSITIVE LOGITS
    改
    0.48
    жээ
    0.48
    仪表
    0.45
    𒂠
    0.44
    jobSize
    0.44
     ayrıca
    0.44
    सिले
    0.43
    缴纳
    0.42
     знает
    0.42
     ओ
    0.42
    Activations Density 0.001%

    No Known Activations