© 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. 275
    Prev
    Next
    INDEX
    Explanations

    youtube video urls

    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
    י
    0.90
    ে
    0.83
    น่า
    0.82
     mechanically
    0.78
    e
    0.77
     allot
    0.75
     refer
    0.73
    น
    0.73
     SON
    0.73
     nă
    0.71
    POSITIVE LOGITS
    iaz
    1.24
    unk
    1.22
    atch
    1.16
    achel
    1.10
    ilon
    1.10
    iffen
    1.09
    inda
    1.09
    olf
    1.08
    ensington
    1.08
    arks
    1.08
    Activations Density 0.625%

    No Known Activations