© 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. 83154
    Prev
    Next
    INDEX
    Explanations

    graduated from or said goodbye to

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

    based on or driven by

    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
    鎗
    0.47
     কর্মীদের
    0.46
     ခု
    0.46
    ٹس
    0.45
     দ্বিতীয়
    0.45
     অভিম
    0.45
     உண்
    0.44
     efficiencies
    0.44
     χρησιμοποι
    0.44
    acés
    0.43
    POSITIVE LOGITS
    Structure
    0.54
    -
    0.53
    Start
    0.51
    Network
    0.50
    Development
    0.49
    Lab
    0.49
    Laboratory
    0.47
    Here
    0.46
    Typography
    0.46
     Academy
    0.45
    Activations Density 0.000%

    No Known Activations