© 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. 49123
    Prev
    Next
    INDEX
    Explanations

    South Africa

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

    praying for publication

    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
     sportive
    0.52
    plastic
    0.48
    ربی
    0.47
     leuke
    0.45
    spor
    0.44
    hockey
    0.44
    و
    0.44
    physical
    0.44
    negative
    0.44
    selective
    0.44
    POSITIVE LOGITS
     Edward
    0.46
     दिरहम
    0.44
     Rodr
    0.43
     subprocess
    0.43
    िएगा
    0.43
     Эд
    0.42
     सीक्व
    0.42
    苋
    0.41
     Rusty
    0.41
     Edmund
    0.41
    Activations Density 0.000%

    No Known Activations