© 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. 1111
    Prev
    Next
    INDEX
    Explanations

    multi-script linguistic elements

    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
    +
    0.46
     pre
    0.46
    ation
    0.44
    ck
    0.42
    isen
    0.41
     proverbial
    0.41
    ight
    0.41
    ating
    0.41
    _
    0.40
    -
    0.40
    POSITIVE LOGITS
    況
    0.61
    ayvachi
    0.60
     पजल
    0.58
     ആവശ
    0.56
    ównie
    0.55
    роят
    0.54
    心が
    0.54
     प्राणियों
    0.53
    Università
    0.53
     সিরাপ
    0.53
    Activations Density 0.030%

    No Known Activations