© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 128950
    Prev
    Next
    INDEX
    Explanations

    extension module, message body, dishwasher pods

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

    technical terms and concepts

    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
    τρ
    0.50
    ar
    0.50
    氤
    0.49
    ffmpeg
    0.48
    is
    0.48
    Respiratory
    0.48
    fors
    0.47
    머니
    0.46
    妪
    0.46
    Effects
    0.46
    POSITIVE LOGITS
     自転車
    0.61
     ライト
    0.55
     スチール
    0.55
     ปุ่ม
    0.54
     グ
    0.54
     層
    0.53
     する
    0.50
     lampe
    0.50
     者
    0.50
     cliquez
    0.50
    Activations Density 0.000%

    No Known Activations