© 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. 500
    Prev
    Next
    INDEX
    Explanations

    German verbs and nouns

    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
     Эд
    0.62
    Э
    0.60
    Vý
    0.60
     Ав
    0.59
     Ше
    0.59
     Си
    0.59
    Ма
    0.59
    Б
    0.58
     Фе
    0.58
     Ар
    0.58
    POSITIVE LOGITS
     kan
    0.44
     er
    0.44
     kunne
    0.41
     får
    0.40
     har
    0.40
     i
    0.38
     bliver
    0.38
     blir
    0.38
     står
    0.37
     på
    0.36
    Activations Density 0.019%

    No Known Activations