© 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. 33084
    Prev
    Next
    INDEX
    Explanations

    request for demo, appointments, services, access

    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
    '
    0.77
    য়া
    0.75
    <0x80>
    0.73
    لم
    0.70
    >
    0.67
    うちに
    0.66
    的大
    0.64
    主席
    0.63
    거운
    0.62
    ají
    0.62
    POSITIVE LOGITS
     Request
    1.26
    Request
    1.15
     request
    1.11
     Requests
    1.10
    request
    1.08
    d
    1.05
     requests
    1.00
     REQUEST
    0.99
     请求
    0.98
    REQUEST
    0.90
    Activations Density 0.065%

    No Known Activations