© 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. 194201
    Prev
    Next
    INDEX
    Explanations

    festival or dumpster rentals

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

    Manchester of South India

    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
     construir
    0.52
    সংখ্যক
    0.51
    constructing
    0.49
     aumentar
    0.48
     constru
    0.48
     incrementar
    0.47
    constru
    0.46
    -‘
    0.45
     risorse
    0.45
    ەس
    0.45
    POSITIVE LOGITS
     場
    0.44
     엔
    0.43
     कंध
    0.42
     গোলাম
    0.42
     Gorman
    0.41
     Pohl
    0.41
    Kont
    0.41
    َت
    0.41
    ता
    0.40
     दिनांक
    0.39
    Activations Density 0.000%

    No Known Activations