© 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. 179333
    Prev
    Next
    INDEX
    Explanations

    fiber, pagan, alive, builds, course, project

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

    PageRank, navigate, growth

    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
     порядок
    0.50
    ೊಂಡು
    0.47
    áticos
    0.46
     имеет
    0.46
     português
    0.46
    暠
    0.46
     imaju
    0.45
    íticos
    0.45
     Carey
    0.45
    ીએ
    0.45
    POSITIVE LOGITS
    bl
    0.48
     dosen
    0.48
    arai
    0.45
     consecut
    0.44
    ਚ
    0.44
    jewelry
    0.43
    pl
    0.43
     algorit
    0.43
     rinsed
    0.43
    jn
    0.42
    Activations Density 0.001%

    No Known Activations