© 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. 99947
    Prev
    Next
    INDEX
    Explanations

    currency amounts and percentages

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

    price and value

    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
     ねえ
    0.51
    मर्द
    0.48
     ۲۰
    0.47
    这些人
    0.47
    佣
    0.47
     salarié
    0.46
    ključ
    0.46
     अफेयर्स
    0.46
    ChooseServer
    0.46
     मंत्रि
    0.44
    POSITIVE LOGITS
    數
    0.45
     massive
    0.44
    0.44
     Re
    0.42
     De
    0.42
     q
    0.42
     subtle
    0.41
     S
    0.41
     widespread
    0.41
     unrelenting
    0.40
    Activations Density 0.002%

    No Known Activations