© 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. 231320
    Prev
    Next
    INDEX
    Explanations

    gaming performance or results

    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
     인한
    0.59
    쯜
    0.54
    碚
    0.52
     abordagem
    0.51
     Tübingen
    0.51
     Cochrane
    0.49
     Tutt
    0.49
     осві
    0.48
    遑
    0.48
     বুদ্ধ
    0.47
    POSITIVE LOGITS
    ↵
    0.61
     running
    0.54
     Stage
    0.46
    lander
    0.45
     /
    0.45
    Stage
    0.44
     ran
    0.44
     holding
    0.43
    running
    0.42
     joined
    0.42
    Activations Density 0.001%

    No Known Activations