© 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. 8986
    Prev
    Next
    INDEX
    Explanations

    die / der noun

    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
     ваш
    0.73
     іх
    0.72
    ô
    0.66
    妇
    0.63
     τις
    0.63
    ctx
    0.62
    apest
    0.60
    orat
    0.60
    érica
    0.58
    몬
    0.58
    POSITIVE LOGITS
     beiden
    1.26
     verwendeten
    1.16
     letzten
    1.15
     wichtigsten
    1.13
     sogenannten
    1.11
     kleinen
    1.08
     genannten
    1.07
     meisten
    1.06
     ersten
    1.05
     zweiten
    1.05
    Activations Density 0.060%

    No Known Activations