© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9654
    Prev
    Next
    INDEX
    Explanations

    architecture and teaching

    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
    ו
    2.59
    i
    2.53
    ه
    2.51
    ر
    2.49
    en
    2.48
    ра
    2.48
    र
    2.40
    a
    2.37
    ‌
    2.33
    ার
    2.29
    POSITIVE LOGITS
    ত্ব
    2.44
    𝘦
    2.41
    颊
    2.40
    ार्किक
    2.36
    袢
    2.33
    𝕣
    2.30
    åll
    2.27
    𝘰
    2.26
    اں
    2.25
    ल्क
    2.23
    Activations Density 0.561%

    No Known Activations