© 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. 1895
    Prev
    Next
    INDEX
    Explanations

    considered as a

    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
     I
    0.92
    I
    0.83
     M
    0.77
    J
    0.75
    os
    0.74
    /
    0.74
    La
    0.73
    we
    0.71
    ia
    0.71
    if
    0.71
    POSITIVE LOGITS
     adenine
    1.26
    一种
    1.25
     scalable
    1.25
     purely
    1.25
     ampere
    1.24
     cohesive
    1.23
     ഒരു
    1.21
    一種
    1.21
     하나의
    1.20
     coherent
    1.20
    Activations Density 0.864%

    No Known Activations