© 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. 13525
    Prev
    Next
    INDEX
    Explanations

    Once I have a sensecurious scholar

    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
     crianças
    1.81
    দিত
    1.78
    pessoas
    1.76
    okit
    1.74
    ുമിത്ര
    1.74
    ൮
    1.74
    crets
    1.73
     pessoa
    1.73
    tableLayoutPanel
    1.73
     pessoas
    1.70
    POSITIVE LOGITS
    <strong>
    1.36
    Balancer
    1.33
    .)
    1.27
    니다
    1.26
     inter
    1.24
     counter
    1.19
     addressing
    1.18
    Permalink
    1.16
     درصد
    1.15
     +:+
    1.14
    Activations Density 1.149%

    No Known Activations