© 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. 100679
    Prev
    Next
    INDEX
    Explanations

    methods and apparatus

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

    tools and methods

    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
     biologiques
    0.48
    🥤
    0.44
     bloodstream
    0.43
    🍗
    0.41
     biologique
    0.40
     hydrating
    0.40
     petrochemical
    0.40
    तलब
    0.40
     centrifuged
    0.40
     Silent
    0.39
    POSITIVE LOGITS
    untuk
    0.53
     यासाठी
    0.50
    相应的
    0.48
     혹은
    0.48
     이를
    0.47
    际
    0.45
     याबाबत
    0.45
     앞에서
    0.45
     क्रमशः
    0.43
     नीति
    0.43
    Activations Density 0.002%

    No Known Activations