© 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. 35835
    Prev
    Next
    INDEX
    Explanations

    container runtimes orchestration efficiency

    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
     escritores
    0.48
    ↵
    0.47
     estim
    0.44
     critic
    0.43
     Freund
    0.41
     حملہ
    0.41
     Friendship
    0.41
     erhalten
    0.41
     tragic
    0.41
     friendships
    0.41
    POSITIVE LOGITS
    enang
    0.52
    isomer
    0.52
    iata
    0.51
    sa
    0.50
    ן
    0.49
    Lou
    0.48
    စိတ်အပိုင်း
    0.48
    novation
    0.47
    pneum
    0.47
    queous
    0.47
    Activations Density 0.002%

    No Known Activations