© 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. 160866
    Prev
    Next
    INDEX
    Explanations

    EASTER, printing, factories, .com

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

    loss, gradient, definition, description

    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
     aplatis
    0.48
     ficando
    0.47
     interno
    0.47
    하지만
    0.46
    =============
    0.46
     masu
    0.46
     속에
    0.46
     عندي
    0.46
    속
    0.45
     Aralık
    0.45
    POSITIVE LOGITS
    itation
    0.44
     सुनिश्चित
    0.44
     management
    0.43
     synd
    0.43
     außergewöhn
    0.43
    تبه
    0.42
     transmissions
    0.42
     voyages
    0.42
     mạng
    0.42
     microm
    0.42
    Activations Density 0.000%

    No Known Activations