© 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. 998
    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_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
     BRO
    1.08
     Burs
    1.07
     dopamine
    0.97
     burs
    0.96
    <unused281>
    0.91
     Brothers
    0.88
     Deane
    0.88
    9
    0.87
     brothers
    0.86
     grams
    0.86
    POSITIVE LOGITS
     samoz
    0.88
     ilg
    0.77
    केट
    0.76
     ilgi
    0.75
    ขนาด
    0.75
     strutture
    0.74
    Intercept
    0.73
    لاحظ
    0.73
     resta
    0.72
     projeto
    0.70
    Activations Density 0.366%

    No Known Activations