© 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. 16315
    Prev
    Next
    INDEX
    Explanations

    common phrases and collocations

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

    muscle mass

    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
     இப்போது
    0.59
     அற்புதமான
    0.49
     தற்போது
    0.49
     Основ
    0.46
    utiérrez
    0.46
    ė
    0.44
     ആരംഭ
    0.44
     そして
    0.44
    ។
    0.44
     ▶
    0.43
    POSITIVE LOGITS
     govt
    0.49
     crappy
    0.48
     $$$
    0.46
     sewage
    0.45
     churches
    0.45
     isotopes
    0.45
     corporations
    0.45
     prostitutes
    0.45
    좆
    0.44
     kidd
    0.43
    Activations Density 0.015%

    No Known Activations