© 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-65K
    7. 56110
    Prev
    Next
    INDEX
    Explanations

    Summary, CVE, Chemical, Issue description

    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_65k_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
    性
    0.48
    руп
    0.37
     acreage
    0.36
     rq
    0.36
    性と
    0.36
     ليك
    0.36
     comprimento
    0.35
    லைன்
    0.35
    性和
    0.35
     فائل
    0.34
    POSITIVE LOGITS
     ovaj
    0.38
    </h2>
    0.38
    ispiels
    0.37
     Subset
    0.36
     খানকে
    0.35
     similar
    0.35
    izens
    0.34
     more
    0.34
     цьому
    0.34
    youtube
    0.34
    Activations Density 0.006%

    No Known Activations