© 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. 42161
    Prev
    Next
    INDEX
    Explanations

    handles Wi-Fi, manager for, consumer using

    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
     caloric
    0.43
     عليه
    0.42
     zeros
    0.42
     kinase
    0.41
     nascent
    0.41
    鈺
    0.40
     inasmuch
    0.40
     severity
    0.40
     contato
    0.38
     homology
    0.38
    POSITIVE LOGITS
     quãng
    0.44
    𝙲
    0.44
     살펴보도록
    0.43
    ېر
    0.42
    эл
    0.42
    ల్యే
    0.41
    伙伴
    0.40
    क
    0.40
    Parrocchia
    0.40
    Elvis
    0.40
    Activations Density 0.003%

    No Known Activations