© 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. 87578
    Prev
    Next
    INDEX
    Explanations

    Senate version, he had, school helpers

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

    for efficiency

    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
    和
    0.46
    ري
    0.45
    óny
    0.45
    শ্চ
    0.44
    的
    0.43
    的和
    0.42
    θηκαν
    0.42
    SCH
    0.42
    셨
    0.41
    ську
    0.41
    POSITIVE LOGITS
    ukar
    0.47
     เดิน
    0.44
     อังกฤษ
    0.44
     ant
    0.43
     Interchange
    0.43
     Stonehenge
    0.42
     Великобрита
    0.42
     願い
    0.41
     उम्मीद
    0.41
    剐
    0.40
    Activations Density 0.001%

    No Known Activations