© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211854
    Prev
    Next
    INDEX
    Explanations

    verbs following chosen, seated, revealed, names, audience

    np_acts-logits-general · gemini-2.5-flash-lite

    this prevents or to prolong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    꼭
    0.55
     oscuro
    0.50
    RAY
    0.46
     obe
    0.44
    پاک
    0.44
    妝
    0.44
     কন্যার
    0.43
     stari
    0.43
    Ц
    0.43
    苏
    0.43
    POSITIVE LOGITS
     ブラ
    0.52
    Editorial
    0.48
     ማ
    0.47
    zept
    0.47
     трёх
    0.46
    LastError
    0.46
    showerror
    0.46
     最後
    0.44
    rror
    0.44
    GetName
    0.44
    Activations Density 0.000%

    No Known Activations