© 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. 194460
    Prev
    Next
    INDEX
    Explanations

    immediately absorbed

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

    general context

    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
     Joon
    0.49
     IJ
    0.48
     Sampson
    0.46
    DAYS
    0.45
     Petersburg
    0.44
     Elias
    0.44
     Hicks
    0.44
    惜
    0.43
     Martins
    0.43
     ஆண்டுகளுக்கு
    0.43
    POSITIVE LOGITS
     બિ
    0.45
     식이
    0.45
     शीघ्र
    0.45
     تعالی
    0.44
     библиотека
    0.43
    pubescens
    0.43
     फ्रैक्शन
    0.42
    ۔
    0.42
    legislation
    0.42
    itatis
    0.42
    Activations Density 0.000%

    No Known Activations