© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1308
    Prev
    Next
    INDEX
    Explanations

    expanding, changing, summing, ordering, refining

    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
    RELATIVA
    0.60
    zada
    0.58
     razie
    0.56
     uchun
    0.53
    ONTAL
    0.53
     Zool
    0.53
     başlayalım
    0.53
    듕
    0.52
     kvadrat
    0.51
    FUENTE
    0.51
    POSITIVE LOGITS
    ने
    0.49
    ባ
    0.43
    িয়ে
    0.43
     tends
    0.43
    지
    0.42
    ना
    0.42
    는지
    0.41
    い
    0.41
    는데
    0.40
     gives
    0.39
    Activations Density 0.013%

    No Known Activations