© 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. 16-GEMMASCOPE-2-RES-262K
    7. 35614
    Prev
    Next
    INDEX
    Explanations

    state legislatures enacting laws

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    1
    1.16
    ه
    0.95
    ۹
    0.80
    ס
    0.78
     at
    0.77
    an
    0.77
    a
    0.77
    5
    0.77
    anın
    0.76
     or
    0.76
    POSITIVE LOGITS
    ли
    0.86
     legislature
    0.70
    ling
    0.68
    ra
    0.68
    기
    0.67
     Итали
    0.67
     लिए
    0.64
    ss
    0.63
     tropics
    0.63
    ri
    0.63
    Activations Density 0.000%

    No Known Activations