© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199472
    Prev
    Next
    INDEX
    Explanations

    risk and reward

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

    built on

    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
    芊
    0.52
     элементов
    0.49
     aján
    0.49
    मिटेड
    0.48
    бля
    0.47
    㭂
    0.47
    StarCore
    0.47
    淤
    0.47
    🍌
    0.47
    𝘔
    0.47
    POSITIVE LOGITS
     steadily
    0.50
    irla
    0.50
    aut
    0.49
     alarm
    0.48
    col
    0.46
     insult
    0.46
     australia
    0.46
     agile
    0.46
     on
    0.46
     dispute
    0.45
    Activations Density 0.000%

    No Known Activations