© 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. 158666
    Prev
    Next
    INDEX
    Explanations

    oil futures, Bible study, Ann Rogers

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

    e-commerce traffic

    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
    ORD
    0.49
    মার
    0.49
    תי
    0.49
     soltanto
    0.48
    Ал
    0.48
    ▦
    0.47
    ONLY
    0.47
    Thời
    0.47
    حدیث
    0.46
    SKIP
    0.45
    POSITIVE LOGITS
    za
    0.49
    ppe
    0.49
    ûr
    0.47
     ifs
    0.46
    嶼
    0.44
    ure
    0.44
    oria
    0.44
    cta
    0.44
     phosphate
    0.43
    đe
    0.43
    Activations Density 0.000%

    No Known Activations