© 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. 190620
    Prev
    Next
    INDEX
    Explanations

    business reports

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

    insert, add, and record information

    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
    ری
    0.54
    Vik
    0.53
    ک
    0.52
    ก
    0.52
    งาน
    0.50
    Შ
    0.50
    راث
    0.50
    Xem
    0.50
    ੀ
    0.49
    Nguyen
    0.48
    POSITIVE LOGITS
     gratification
    0.45
     hr
    0.42
     depots
    0.41
    ppling
    0.41
     تلك
    0.41
     fie
    0.40
     mq
    0.40
     tore
    0.40
     carelessly
    0.40
     denomin
    0.40
    Activations Density 0.001%

    No Known Activations