© 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. 10774
    Prev
    Next
    INDEX
    Explanations

    using code and instructions

    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
    red
    1.42
    𝐯
    1.40
    риев
    1.35
    ĕ
    1.35
    𝐕
    1.32
    𝐡
    1.32
    reed
    1.31
    reden
    1.30
     tackled
    1.28
    ran
    1.28
    POSITIVE LOGITS
     kelu
    1.76
    炲
    1.61
     danne
    1.59
     imports
    1.58
     utilizzare
    1.54
    เกิน
    1.48
     輸入
    1.47
     artificially
    1.45
     eventuali
    1.43
     benign
    1.43
    Activations Density 0.000%

    No Known Activations