© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1117
    Prev
    Next
    INDEX
    Explanations

    adjacency and nearness

    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_17_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
     Ανακτήθηκε
    0.89
     ağırl
    0.86
    δια
    0.80
     kaleidoscope
    0.80
    isset
    0.80
    گانی
    0.80
    enton
    0.79
    <0xB3>
    0.78
    स्त्र
    0.78
    <0xA4>
    0.77
    POSITIVE LOGITS
     near
    3.11
     vicino
    3.01
     nearby
    2.98
     adjacent
    2.91
     perto
    2.87
    ใกล้
    2.82
    near
    2.79
    靠近
    2.78
     dekat
    2.78
     close
    2.73
    Activations Density 2.464%

    No Known Activations