© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 962
    Prev
    Next
    INDEX
    Explanations

    quotation; cultural exploration; javascript code

    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
    laquo
    0.93
     unnecessary
    0.91
     unnecessarily
    0.89
    ="#!"
    0.89
    ും
    0.87
    VALID
    0.86
    constraint
    0.86
     bloss
    0.85
    ಿದರೆ
    0.85
    webstore
    0.84
    POSITIVE LOGITS
    aran
    0.79
     Francisco
    0.78
    nd
    0.75
    th
    0.74
     Z
    0.73
    vens
    0.73
     Roman
    0.72
     गवर्नमेंट
    0.72
     Gu
    0.71
    uble
    0.69
    Activations Density 0.000%

    No Known Activations