© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1571
    Prev
    Next
    INDEX
    Explanations

    body

    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_7_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
    𝗶
    3.71
    𝐢
    3.20
    𝗼
    3.17
    𝗽
    3.15
    𝗲
    3.12
    搬型
    3.12
    𝒊
    3.09
    𝗹
    3.08
    𝘀
    2.98
    𝐭
    2.92
    POSITIVE LOGITS
    an
    3.29
    a
    3.01
    йга
    2.67
    การ
    2.54
    거운
    2.52
    一批
    2.48
    רות
    2.44
    רת
    2.40
    ••••
    2.40
    ymce
    2.37
    Activations Density 0.891%

    No Known Activations