© 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. 1568
    Prev
    Next
    INDEX
    Explanations

    industry expertise and trends

    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
    gomery
    2.36
    antry
    2.35
    chets
    2.16
    ocomplete
    2.02
    ফ
    2.01
    ーフ
    1.97
    umball
    1.97
    虑
    1.95
     throat
    1.91
    लेटर
    1.87
    POSITIVE LOGITS
    sü
    2.85
    dan
    2.83
    daki
    2.77
     laboral
    2.60
    schap
    2.57
    рифмети
    2.54
    निश्ड
    2.54
    das
    2.49
    ların
    2.45
     wèi
    2.45
    Activations Density 0.211%

    No Known Activations