© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4574
    Prev
    Next
    INDEX
    Explanations

    match or incompatible formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     compressibility
    1.47
     parametrization
    1.26
     discourse
    1.25
    軖
    1.24
    机制
    1.24
    partum
    1.23
     arrhythmias
    1.23
     kompon
    1.23
    nlp
    1.22
     linguistics
    1.21
    POSITIVE LOGITS
     eye
    1.44
     Eye
    1.42
     eyes
    1.37
     EYE
    1.33
     ocul
    1.32
    眼
    1.29
    eyes
    1.28
     Eyes
    1.26
     mắt
    1.26
     Ey
    1.26
    Activations Density 0.315%

    No Known Activations