© 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. 208932
    Prev
    Next
    INDEX
    Explanations

    agreement or removal

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

    pricing, requires, ethics

    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
    你不
    0.54
    不存在
    0.48
    值为
    0.48
    爱你
    0.48
    锗
    0.48
    第二次
    0.46
    ђу
    0.46
    仅
    0.45
    あなた
    0.45
    FileCopy
    0.45
    POSITIVE LOGITS
     DEL
    0.62
    is
    0.55
     klar
    0.52
     boute
    0.50
    ost
    0.50
    لف
    0.48
    inov
    0.47
    ring
    0.47
     debate
    0.46
     kong
    0.46
    Activations Density 0.001%

    No Known Activations