© 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. 114681
    Prev
    Next
    INDEX
    Explanations

    real, seen, affecting, Time, Every, spent, Extreme, more

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

    relational database

    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
    SetStr
    0.57
    𝚙
    0.56
    婍
    0.52
    Amat
    0.49
    (",");
    0.48
    스가
    0.48
    KeepOriginal
    0.47
    扇
    0.47
    ストラ
    0.47
    ostr
    0.46
    POSITIVE LOGITS
     heats
    0.48
     Pric
    0.48
     Silica
    0.48
     Selection
    0.48
     Changing
    0.47
     holds
    0.46
     está
    0.45
     Wheel
    0.45
     species
    0.45
     Redwood
    0.45
    Activations Density 0.000%

    No Known Activations