© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 28561
    Prev
    Next
    INDEX
    Explanations

    cosmic, celestial, galactic beings

    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
     служба
    0.54
    铳
    0.52
     الناس
    0.51
    ాయి
    0.47
     لڑکی
    0.47
     డబ్బు
    0.46
    ওয়্যার
    0.46
    铰
    0.46
     পরিষ্কার
    0.46
     چیز
    0.45
    POSITIVE LOGITS
     cosmic
    0.61
     celestial
    0.59
     galactic
    0.57
     करोड़ों
    0.56
     beings
    0.55
     lineages
    0.55
     Cosmic
    0.53
     ancient
    0.52
     epochs
    0.52
     ascend
    0.52
    Activations Density 0.072%

    No Known Activations