© 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. 228823
    Prev
    Next
    INDEX
    Explanations

    words indicating specific items

    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
     Anakin
    0.58
    ี้
    0.51
     ஐந்து
    0.49
     Escobar
    0.47
    ىسى
    0.47
    囪
    0.47
     Doesn
    0.46
     Advisor
    0.46
     Skywalker
    0.46
     Sı
    0.45
    POSITIVE LOGITS
     न्यूयॉर्क
    0.46
     alrededores
    0.45
    rda
    0.44
     newspap
    0.44
    lardır
    0.44
    lications
    0.43
    ନ୍ଦ
    0.43
    RELATES
    0.43
    ㅀ
    0.42
    ্লি
    0.42
    Activations Density 0.000%

    No Known Activations