© 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. 20911
    Prev
    Next
    INDEX
    Explanations

    develop AI

    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
    ್ರ
    0.52
     senseless
    0.47
     божомолдор
    0.46
    <0x11>
    0.46
    lai
    0.45
    顎
    0.45
     menstrual
    0.45
     bicovariant
    0.44
    ឡិច
    0.44
     SimSun
    0.43
    POSITIVE LOGITS
    SPF
    0.46
     Spokane
    0.44
     garçon
    0.43
     Gron
    0.43
     gratuits
    0.42
    住宅
    0.41
     Pullman
    0.41
    ጨ
    0.41
    方
    0.40
     Strand
    0.40
    Activations Density 0.025%

    No Known Activations