© 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. 22-GEMMASCOPE-2-RES-16K
    7. 682
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
     twos
    1.19
     `<`,
    1.13
     ಎರಡು
    1.12
    <unused1963>
    1.12
     nameWithOwner
    1.11
     四
    1.11
    <unused117>
    1.10
    িয়াছিলেন
    1.10
     两
    1.08
    اونلوډ
    1.08
    POSITIVE LOGITS
    3
    1.45
    <unused62>
    0.93
    5
    0.92
    ë
    0.89
    8
    0.89
    9
    0.89
    4
    0.89
    6
    0.87
    <eos>
    0.86
     Mor
    0.85
    Activations Density 1.243%

    No Known Activations