© 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. 1596
    Prev
    Next
    INDEX
    Explanations

    STEM fields and robotics

    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
    ਏ
    1.26
    YEAR
    1.22
     poisoned
    1.16
     captured
    1.13
     anything
    1.11
     hurt
    1.11
     nimic
    1.07
    নেই
    1.06
    errors
    1.05
    arrayOf
    1.03
    POSITIVE LOGITS
    ̣t
    1.77
     PCE
    1.63
    𐰴
    1.62
     Differentiation
    1.60
     Hypot
    1.60
    ratic
    1.59
     GE
    1.57
    bé
    1.55
    帕
    1.55
    monte
    1.54
    Activations Density 0.000%

    No Known Activations