© 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. 154241
    Prev
    Next
    INDEX
    Explanations

    quality materials

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

    reward for work, depending on usage

    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
     Salazar
    0.49
    sparsebundle
    0.49
    م
    0.47
     hordes
    0.47
    setImageResource
    0.47
    מ
    0.46
     lockers
    0.46
    os
    0.46
    िम
    0.46
    capture
    0.45
    POSITIVE LOGITS
    滔
    0.47
    篙
    0.47
    IELD
    0.46
    睡觉
    0.46
    рий
    0.46
    跑到
    0.46
    工人
    0.46
    能够在
    0.45
     торговли
    0.44
    arios
    0.44
    Activations Density 0.003%

    No Known Activations