© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136843
    Prev
    Next
    INDEX
    Explanations

    cash machines, astrology, complexity

    np_acts-logits-general · gemini-2.5-flash-lite

    Xiao Liuren divination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     갔다
    0.44
    毬
    0.44
    博物
    0.44
     Nghị
    0.44
     기울
    0.42
     लिखे
    0.42
    erçe
    0.41
    的思想
    0.41
    MAPb
    0.41
    ılığı
    0.41
    POSITIVE LOGITS
     abon
    0.56
    ت
    0.55
    kali
    0.49
    Subscribe
    0.48
     Clas
    0.46
     Ander
    0.45
     Glas
    0.44
     irr
    0.43
    projekt
    0.43
    тун
    0.43
    Activations Density 0.001%

    No Known Activations