© 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. 165069
    Prev
    Next
    INDEX
    Explanations

    years ago, save lives, Mario Kart, below industry

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

    TensorFlow and economic growth

    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
    ম্যান
    0.49
    ⓞ
    0.49
     nitrification
    0.47
     réel
    0.46
     nitric
    0.45
     supernovae
    0.44
     convolution
    0.44
     formulae
    0.44
     territo
    0.43
     dienst
    0.43
    POSITIVE LOGITS
     ז
    0.54
    itated
    0.52
    胰
    0.46
     ކުރ
    0.45
    inated
    0.44
    ḗ
    0.43
     Hil
    0.43
     על
    0.43
     McKin
    0.42
     :=
    0.42
    Activations Density 0.000%

    No Known Activations