© 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. 122063
    Prev
    Next
    INDEX
    Explanations

    work, cleared, boat, factory

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

    sufficient for

    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
    一边
    0.52
     点击
    0.50
     半
    0.50
    开始
    0.47
     হলেই
    0.47
     定
    0.46
     نیم
    0.46
     Anglia
    0.45
     画
    0.45
    ایج
    0.45
    POSITIVE LOGITS
    mailed
    0.50
    challenges
    0.49
    sticky
    0.48
    municipal
    0.48
     район
    0.46
    não
    0.45
    funding
    0.44
    thunder
    0.44
     challenges
    0.44
    racial
    0.44
    Activations Density 0.001%

    No Known Activations