© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3716
    Prev
    Next
    INDEX
    Explanations

    technical terms after "the"

    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
     그리고
    1.92
    떤
    1.88
     및
    1.84
     以及
    1.80
     工程
    1.76
     ಮತ್ತು
    1.73
    그리고
    1.73
    년대
    1.71
    페
    1.70
    rave
    1.69
    POSITIVE LOGITS
    ariate
    1.65
     subsid
    1.56
    cini
    1.48
     politici
    1.46
     primacy
    1.45
    ন্স
    1.45
     HttpException
    1.44
     auxili
    1.42
     glBind
    1.42
     autoridad
    1.42
    Activations Density 0.048%

    No Known Activations