© 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. 14835
    Prev
    Next
    INDEX
    Explanations

    aquarium of, reminder that, photos taken, sound effect

    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
    ”
    2.57
    ,”
    2.42
     “
    2.40
     ”
    2.35
    ’’
    2.30
    ¸
    2.28
    ิ
    2.22
    :”
    2.20
    थि
    2.20
    ”,
    2.16
    POSITIVE LOGITS
     alamu
    2.91
    ખ્ય
    2.89
    ំពោះ
    2.86
     tratti
    2.74
    olič
    2.69
    VersionUID
    2.66
     ลํา
    2.65
    sberg
    2.62
    迪士
    2.62
    panelMenuList
    2.60
    Activations Density 0.003%

    No Known Activations