© 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. 844
    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
     сельскохозяй
    0.89
    農
    0.86
     경찰
    0.86
    clearInterval
    0.86
     Bolts
    0.86
    County
    0.85
    텃
    0.85
     полицей
    0.84
    Polic
    0.84
    枸
    0.84
    POSITIVE LOGITS
     Audio
    2.22
     preamp
    2.15
     audio
    2.08
     headphone
    2.03
    Audio
    2.02
     AUDIO
    1.96
     audi
    1.95
    audio
    1.93
     subwoofer
    1.91
     loudspeaker
    1.89
    Activations Density 1.889%

    No Known Activations