© 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. 64295
    Prev
    Next
    INDEX
    Explanations

    data such as

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

    Gmail, SD, articles

    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
    ize
    0.49
     ও
    0.46
     ایسے
    0.45
    啥
    0.45
    std
    0.45
     व
    0.44
     std
    0.44
    stituto
    0.44
    .??
    0.44
    kJ
    0.43
    POSITIVE LOGITS
    行って
    0.42
    大きな
    0.41
     capitalismo
    0.41
    amending
    0.41
    採
    0.40
    傑
    0.40
     Glasgow
    0.38
     電
    0.38
    ふ
    0.38
    樫
    0.38
    Activations Density 0.000%

    No Known Activations