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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70316
    Prev
    Next
    INDEX
    Explanations

    seeks to control or conquer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sighed
    2.05
     strugg
    1.95
     forfe
    1.92
     succumbed
    1.92
     forfeited
    1.89
     groaned
    1.89
    otard
    1.86
    恹
    1.86
    只好
    1.85
     doh
    1.85
    POSITIVE LOGITS
    filter
    1.54
     Internet
    1.41
    VAR
    1.34
     Men
    1.34
    customers
    1.32
    rs
    1.31
     Customers
    1.30
    Hy
    1.28
     customers
    1.28
     President
    1.28
    Activations Density 0.000%

    No Known Activations