© 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. 879
    Prev
    Next
    INDEX
    Explanations

    self-possession or personal attribute

    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
     całym
    1.51
     presentó
    1.45
     escolas
    1.35
     crianças
    1.35
    Intersect
    1.34
    eket
    1.33
     tengamos
    1.32
    Ế
    1.32
     különböző
    1.32
     υπάρχει
    1.31
    POSITIVE LOGITS
     personal
    1.44
    ្រ
    1.40
     private
    1.27
     internal
    1.26
    own
    1.26
    initiative
    1.20
    몫
    1.19
    sohn
    1.18
    ständig
    1.18
    igene
    1.14
    Activations Density 0.523%

    No Known Activations