© 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. 13865
    Prev
    Next
    INDEX
    Explanations

    Flag to

    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
    uvre
    2.91
     vsize
    2.87
    畢
    2.69
    ᆭ
    2.63
    UFACT
    2.60
    াগ
    2.58
    ත්මක
    2.56
    nuxtjs
    2.36
    ঞ্চল্য
    2.34
    色列
    2.33
    POSITIVE LOGITS
    “”
    2.83
    帜
    2.79
    دار
    2.69
    bed
    2.68
    dok
    2.64
    ば
    2.64
    。“
    2.57
    ellum
    2.56
    ，“
    2.51
    trt
    2.51
    Activations Density 0.004%

    No Known Activations