© 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. 43121
    Prev
    Next
    INDEX
    Explanations

    Amaziah king of Judah

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

    list items or bullet points

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Gertrude
    0.52
     लियो
    0.52
    ละคร
    0.52
     Gemma
    0.47
     Hatteras
    0.46
    朐
    0.46
     Macbeth
    0.45
     Leandro
    0.45
     Giacomo
    0.45
     Katharine
    0.42
    POSITIVE LOGITS
    OM
    0.54
    K
    0.54
    KU
    0.52
    Ин
    0.48
    Buk
    0.48
    平时
    0.48
    O
    0.46
    去
    0.46
    يزة
    0.46
    kunde
    0.45
    Activations Density 0.001%

    No Known Activations