© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9589
    Prev
    Next
    INDEX
    Explanations

    general knowledge and guidance

    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
    CBS
    1.11
     Kiel
    1.09
     REPUBLIC
    1.09
    removeItem
    1.03
    肖
    1.00
     Unwrap
    1.00
     صاد
    0.99
    ibouti
    0.98
    είο
    0.98
     Zimm
    0.98
    POSITIVE LOGITS
    憊
    1.90
    倦
    1.84
     fatigued
    1.69
     exhaustion
    1.61
     थकान
    1.54
     ক্লান্ত
    1.51
    疲れ
    1.50
     Tired
    1.49
     थक
    1.46
     weary
    1.45
    Activations Density 0.317%

    No Known Activations