© 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. 43496
    Prev
    Next
    INDEX
    Explanations

    articles and determiners

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

    up on, recorded, spontaneity

    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
     ኢ
    0.46
     пише
    0.46
     пишу
    0.45
     ইন্ডাস্ট
    0.44
     इनवर्स
    0.44
     எழுது
    0.44
     ವಸ್ತು
    0.44
     LAST
    0.44
    writes
    0.44
     viktigt
    0.44
    POSITIVE LOGITS
    也能
    0.48
    ও
    0.46
     suites
    0.44
     phù
    0.43
     sentido
    0.43
     duen
    0.43
     কিছুটা
    0.43
    một
    0.42
    ちょっと
    0.41
     suite
    0.41
    Activations Density 0.000%

    No Known Activations