© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 301
    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
     massacre
    1.42
    <unused2177>
    1.40
     Hitler
    1.39
     死
    1.35
     fascist
    1.34
     지금
    1.34
     perilous
    1.33
     Nazi
    1.31
     몇
    1.30
    <unused1189>
    1.30
    POSITIVE LOGITS
    same
    1.04
     соответственно
    1.02
    another
    1.00
      
    0.98
    along
    0.96
    anto
    0.91
    ano
    0.91
    また
    0.90
    ore
    0.90
     మరో
    0.89
    Activations Density 0.578%

    No Known Activations