© 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. 15608
    Prev
    Next
    INDEX
    Explanations

    what it is

    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
    lection
    2.62
     Deduction
    2.57
    次方
    2.55
    蒾
    2.53
    пан
    2.52
    нгтон
    2.52
    んばんは
    2.50
     Depth
    2.47
    郸
    2.46
    ৬
    2.46
    POSITIVE LOGITS
    ni
    2.36
    r
    2.10
     đạp
    2.06
    ್ಣ
    2.05
    툴
    1.96
    FormatException
    1.94
    ン
    1.88
    𝗋
    1.87
    ە
    1.87
    ্ষিক
    1.87
    Activations Density 0.084%

    No Known Activations