© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 153
    Prev
    Next
    INDEX
    Explanations

    naming, German suffixes, Russian cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     Қ
    0.59
    Қ
    0.56
    ری
    0.50
     Ми
    0.48
     Ди
    0.48
    И
    0.48
     Ме
    0.48
    Ми
    0.48
    Ма
    0.48
     Ин
    0.48
    POSITIVE LOGITS
     nie
    0.37
     dokładnie
    0.36
     dzięki
    0.36
     po
    0.35
     dużo
    0.34
     poch
    0.33
     jednak
    0.33
     choć
    0.33
     już
    0.32
     dość
    0.32
    Activations Density 0.047%

    No Known Activations