© 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. 152671
    Prev
    Next
    INDEX
    Explanations

    business relationships

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

    MB, log, LETTERS, SELECT

    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
     चैंपियन
    0.52
    BTW
    0.50
    ới
    0.46
    pron
    0.46
    Premium
    0.46
    School
    0.45
    v
    0.44
     incons
    0.44
    сё
    0.44
     teamTable
    0.43
    POSITIVE LOGITS
     완전히
    0.51
     blockchain
    0.47
     ū
    0.47
     একজনকে
    0.46
     تنها
    0.46
     কেবলমাত্র
    0.45
     vorgesehen
    0.44
     Einsatz
    0.43
     مالک
    0.43
     seulement
    0.42
    Activations Density 0.001%

    No Known Activations