© 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. 15474
    Prev
    Next
    INDEX
    Explanations

    peak season is busy

    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
    י
    3.44
    ি
    3.18
    sG
    3.03
    s
    3.01
    ब्ल्यू
    2.97
    𝐞
    2.96
    ske
    2.95
    ാ
    2.95
    tap
    2.92
    ен
    2.91
    POSITIVE LOGITS
    ...*/
    3.00
    োহণ
    2.81
    ণ্য
    2.70
    #__
    2.38
    कीय
    2.32
    hesized
    2.30
    şehir
    2.28
     einzelne
    2.23
    icket
    2.20
    ächen
    2.18
    Activations Density 0.066%

    No Known Activations