© 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. 31454
    Prev
    Next
    INDEX
    Explanations

    connectivity and rise

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

    cost savings and competitive spirit

    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
     Một
    0.54
     Hug
    0.50
     Cliente
    0.50
     IPC
    0.50
     Chirurgien
    0.50
     Especial
    0.50
     Of
    0.49
     ط
    0.49
    Clientes
    0.49
     διε
    0.49
    POSITIVE LOGITS
    อด
    0.42
    DebugSymbols
    0.42
    ｭ
    0.42
    erings
    0.41
    achery
    0.41
    ллин
    0.40
    ód
    0.40
    ब्लिक
    0.40
    ЕР
    0.40
    ేవ
    0.39
    Activations Density 0.000%

    No Known Activations