© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144346
    Prev
    Next
    INDEX
    Explanations

    system, constant, progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    걸
    0.54
     metà
    0.52
    9
    0.52
    ৭
    0.52
    5
    0.50
    ধে
    0.49
     mercado
    0.48
    ル
    0.48
     politiche
    0.47
    pharmac
    0.47
    POSITIVE LOGITS
     обеспечения
    0.43
     Pascal
    0.42
    ीय
    0.42
     、,
    0.41
     అందించ
    0.41
    ittee
    0.41
     выбора
    0.41
     didn
    0.41
     flask
    0.41
    ASCADE
    0.41
    Activations Density 0.001%

    No Known Activations