© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2539
    Prev
    Next
    INDEX
    Explanations

    font-family

    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
     аласыз
    0.59
     ECB
    0.55
    etat
    0.55
    юм
    0.55
    elő
    0.53
    予
    0.53
     অ্যাল
    0.53
     Đông
    0.53
     Fli
    0.53
    鬟
    0.52
    POSITIVE LOGITS
    tene
    0.74
     ti
    0.71
    tar
    0.70
    tch
    0.67
    tsk
    0.66
     tuk
    0.66
     tar
    0.63
     idiot
    0.63
     alleine
    0.62
     tk
    0.62
    Activations Density 0.186%

    No Known Activations