© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10952
    Prev
    Next
    INDEX
    Explanations

    Newer post titles

    np_acts-logits-general · gemini-2.5-flash-lite

    pagination and pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
     comentado
    0.43
    Descripción
    0.41
    滁
    0.40
    વારે
    0.40
    Коммента
    0.39
     Kommentar
    0.38
    Uploaded
    0.38
    鬓
    0.38
     Chayin
    0.38
     comentar
    0.37
    POSITIVE LOGITS
     load
    0.67
     Load
    0.65
     Loads
    0.65
    Load
    0.63
     loads
    0.61
    load
    0.61
    loads
    0.58
     LOAD
    0.57
    加载
    0.55
     more
    0.54
    Activations Density 0.006%

    No Known Activations