© 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. 8103
    Prev
    Next
    INDEX
    Explanations

    introductions, officers, surfaces

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

    Important considerations and principles

    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
     atau
    0.55
     vagy
    0.48
    または
    0.48
    或
    0.48
     ще
    0.47
     veya
    0.46
            
    0.45
    или
    0.45
     enti
    0.45
     doda
    0.45
    POSITIVE LOGITS
    들을
    0.39
     INTRODUCTION
    0.38
    리를
    0.38
     OFFICER
    0.38
    }}^{(
    0.37
     INSPE
    0.37
     SURFACE
    0.37
     KPK
    0.37
    ुप
    0.37
    __':
    0.37
    Activations Density 0.000%

    No Known Activations