© 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. 131559
    Prev
    Next
    INDEX
    Explanations

    people and proper names

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

    ETL, gold, watch

    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
     b
    0.48
     ||
    0.45
     za
    0.45
     y
    0.43
     bt
    0.41
     tyrannical
    0.41
     బ
    0.40
     scourge
    0.40
     sambil
    0.40
    žne
    0.40
    POSITIVE LOGITS
    delicious
    0.47
    mming
    0.46
    ທີ່
    0.45
    矿
    0.45
    क्षेप
    0.44
    Thirty
    0.44
    walled
    0.43
    랫폼
    0.43
    쩌
    0.43
    らせ
    0.43
    Activations Density 0.001%

    No Known Activations