© 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. 7519
    Prev
    Next
    INDEX
    Explanations

    sentence or text structure

    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
    ículo
    1.35
     loafers
    1.33
    皁
    1.32
     опреде
    1.25
     висо
    1.24
    edì
    1.22
     хоро
    1.21
     Yoruba
    1.21
     wale
    1.20
    collegiate
    1.19
    POSITIVE LOGITS
    いき
    0.92
    رشف
    0.89
     Craw
    0.86
     Proceeds
    0.80
     conversion
    0.80
    ੋਰ
    0.80
    진
    0.79
     Fried
    0.79
     Donate
    0.79
     Macht
    0.78
    Activations Density 0.004%

    No Known Activations