© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1297
    Prev
    Next
    INDEX
    Explanations

    frameworks and theories

    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_65k_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
     incroy
    0.92
     horr
    0.84
     terrib
    0.81
     fürs
    0.81
     insiders
    0.80
     tourner
    0.76
    쫙
    0.76
     BEGIN
    0.75
     uite
    0.74
     unleash
    0.71
    POSITIVE LOGITS
     مطالعه
    1.50
     연구
    1.50
     본
    1.48
     민
    1.43
     本
    1.39
     پژوه
    1.38
     苏
    1.38
    본
    1.36
    Studies
    1.35
     소
    1.34
    Activations Density 0.149%

    No Known Activations