© 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. 7604
    Prev
    Next
    INDEX
    Explanations

    key + characteristic

    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
    榈
    2.96
    ı
    2.85
    ிக்க
    2.82
    ља
    2.77
    हेज
    2.64
    sk
    2.63
    ation
    2.61
     ulc
    2.49
    ೀಯ
    2.48
    !/"
    2.46
    POSITIVE LOGITS
    eled
    2.64
    रान
    2.54
    تج
    2.34
    bollah
    2.28
    ៊
    2.28
    chains
    2.27
    hole
    2.27
    ان
    2.26
    ر
    2.22
    델
    2.20
    Activations Density 0.152%

    No Known Activations