© 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. 13484
    Prev
    Next
    INDEX
    Explanations

    even if

    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
    িণী
    3.08
    ت
    2.99
    esinin
    2.65
    ೆಂಟ್
    2.60
    𝐲
    2.60
    sf
    2.52
    ea
    2.52
    eah
    2.46
    esinde
    2.44
    esin
    2.41
    POSITIVE LOGITS
    ＞
    2.64
    」「
    2.54
    vana
    2.52
    ！」
    2.46
    КС
    2.45
    𝐼
    2.44
    мир
    2.43
    だい
    2.34
    」、「
    2.34
    desde
    2.28
    Activations Density 0.013%

    No Known Activations