© 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. 3406
    Prev
    Next
    INDEX
    Explanations

    synaptic plasticity

    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
     Coldplay
    1.67
     teren
    1.64
     WEST
    1.64
     време
    1.62
     Cavaliers
    1.61
     fenomen
    1.60
     CENTER
    1.56
    →</
    1.55
     CUT
    1.54
    тации
    1.53
    POSITIVE LOGITS
    jot
    1.52
    很多的
    1.47
    وسی
    1.46
    తిక
    1.45
    еро
    1.44
    相關文章
    1.43
    aux
    1.41
    automatic
    1.41
    MemoryWarning
    1.40
    chemical
    1.39
    Activations Density 0.097%

    No Known Activations