© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7062
    Prev
    Next
    INDEX
    Explanations

    what you want

    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_13_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
     своему
    1.72
    (/*
    1.60
    。《
    1.50
    (!
    1.49
     ਅਤੇ
    1.48
     ಮತ್ತು
    1.45
     său
    1.45
     („
    1.44
     (!
    1.43
     знамени
    1.43
    POSITIVE LOGITS
    nt
    1.31
    entities
    1.24
    nts
    1.22
    not
    1.21
     %
    1.14
    onda
    1.08
     NOT
    1.06
    pi
    1.05
    ot
    1.05
     TREND
    1.03
    Activations Density 0.085%

    No Known Activations