© 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. 980
    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_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
    mathspace
    1.56
    <unused1173>
    1.55
     hindering
    1.51
    <unused1197>
    1.51
    <unused905>
    1.50
    <unused1174>
    1.48
    <unused1202>
    1.47
    sthresh
    1.46
    <unused1623>
    1.46
    lockSeconds
    1.46
    POSITIVE LOGITS
    In
    0.87
    ）
    0.86
    <eos>
    0.85
    J
    0.82
    さらに
    0.81
     reciente
    0.81
    ↵↵
    0.81
    B
    0.80
     infine
    0.80
    Ent
    0.79
    Activations Density 0.471%

    No Known Activations