© 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. 1465
    Prev
    Next
    INDEX
    Explanations

    leads 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
    ették
    2.67
    anor
    2.56
    ToOne
    2.54
    etiti
    2.53
    ｫ
    2.48
    BURG
    2.42
    setPreferredSize
    2.41
    ετε
    2.38
    Diethyl
    2.36
    तोष
    2.35
    POSITIVE LOGITS
     unem
    2.52
    gara
    2.51
    hhhhhhhh
    2.49
    hhhh
    2.48
    g
    2.46
    تل
    2.39
    dut
    2.34
    ング
    2.32
    gı
    2.30
    زیز
    2.27
    Activations Density 0.344%

    No Known Activations