© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9623
    Prev
    Next
    INDEX
    Explanations

    hex, COUN

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     Nationality
    0.61
    ურთიერთ
    0.55
     συνέχ
    0.54
    皂
    0.54
    圃
    0.52
    คู่
    0.51
    电视剧
    0.50
     tillage
    0.50
    壟
    0.50
     Murat
    0.50
    POSITIVE LOGITS
     hexadecimal
    1.87
     hex
    1.68
    hex
    1.52
     HEX
    1.51
    Hex
    1.50
     Hex
    1.50
    HEX
    1.49
     hexa
    1.38
    进制
    1.30
    HexString
    1.29
    Activations Density 0.040%

    No Known Activations