© 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. 24371
    Prev
    Next
    INDEX
    Explanations

    several board, each year

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

    **Stream**, **Exhibit**, **Power**, **chocolate**, **hot**, **options**

    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
     दु
    0.41
     HOTEL
    0.40
    <0xC8>
    0.40
     हवाले
    0.40
     V
    0.40
    0.40
    U
    0.39
     NEWS
    0.38
     全
    0.38
    之路
    0.38
    POSITIVE LOGITS
    আমাকে
    0.51
     nörd
    0.46
    শ্ত
    0.46
     pecans
    0.45
    ષ્ય
    0.44
    ແລະ
    0.43
    चार्य
    0.43
     ലക്ഷ
    0.43
     굉장히
    0.43
    ক্ষিতে
    0.42
    Activations Density 0.000%

    No Known Activations