© 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. 201
    Prev
    Next
    INDEX
    Explanations

    compared to others

    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
    ,
    0.87
    .
    0.84
    ’
    0.82
    -
    0.81
    og
    0.75
     and
    0.75
    '
    0.74
    ic
    0.74
     в
    0.72
    ut
    0.71
    POSITIVE LOGITS
     autre
    1.50
     andere
    1.49
    其他的
    1.48
     anderen
    1.47
     diğer
    1.46
     başka
    1.43
     سایر
    1.39
    其它
    1.36
     altri
    1.35
     autres
    1.34
    Activations Density 5.400%

    No Known Activations