© 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. 234884
    Prev
    Next
    INDEX
    Explanations

    multi-word phrases and descriptions

    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
    轍
    0.50
    时的
    0.48
    診
    0.47
    рифт
    0.46
     अलग
    0.45
     видели
    0.45
    琢
    0.45
    프트
    0.44
     فريبي
    0.44
     оюн
    0.44
    POSITIVE LOGITS
     can
    0.55
     Orders
    0.55
    ir
    0.55
     is
    0.54
     Only
    0.54
     Sometimes
    0.53
     Trains
    0.53
     Or
    0.52
     doesn
    0.52
     And
    0.51
    Activations Density 0.001%

    No Known Activations