© 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. 237301
    Prev
    Next
    INDEX
    Explanations

    statement through

    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
     вершин
    0.46
     βρί
    0.46
     établissements
    0.45
     empezamos
    0.45
     駅
    0.43
    FDA
    0.43
     промышленности
    0.43
    ASHINGTON
    0.42
     ಗುರು
    0.42
     qubits
    0.42
    POSITIVE LOGITS
    动物
    0.52
     Yearbook
    0.47
    洍
    0.47
    选题
    0.45
    اجة
    0.45
    if
    0.44
     lavoro
    0.44
    货币
    0.44
    情绪
    0.43
    alış
    0.43
    Activations Density 0.000%

    No Known Activations