© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 201062
    Prev
    Next
    INDEX
    Explanations

    foreign words or specific facts

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

    strongest suit, primary research, especially hurtful

    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
    レ
    0.50
    ’
    0.49
    l
    0.48
    /
    0.48
    on
    0.47
    i
    0.46
     sundry
    0.46
     Wells
    0.46
    us
    0.45
    a
    0.45
    POSITIVE LOGITS
     atualmente
    0.56
     Actualmente
    0.53
     सर्वाधिक
    0.49
     때문에
    0.49
     現在
    0.49
     വര്‍ഷ
    0.48
     frequência
    0.47
    ที่สุด
    0.46
     यूक्रेन
    0.45
     worsens
    0.45
    Activations Density 0.002%

    No Known Activations