© 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. 146366
    Prev
    Next
    INDEX
    Explanations

    make any

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

    FcRn, Fold Region, washing dishes, GPT

    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
    ع
    0.66
    ق
    0.62
    م
    0.59
    м
    0.55
     .
    0.50
    Combined
    0.49
     "
    0.48
     sport
    0.48
    <i>
    0.47
    }.
    0.47
    POSITIVE LOGITS
    <unused57>
    0.58
    <unused53>
    0.55
    <unused12>
    0.50
    <unused31>
    0.50
    AppBsky
    0.49
     getUserBy
    0.49
    েন্ড
    0.48
    㻐
    0.48
    <unused77>
    0.48
    мережа
    0.48
    Activations Density 0.000%

    No Known Activations