© 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. 2053
    Prev
    Next
    INDEX
    Explanations

    describing colors and materials

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    椅
    0.88
    厕
    0.84
    后
    0.84
    窓
    0.83
    下げ
    0.83
    入場
    0.83
    例
    0.82
    への
    0.82
     تع
    0.81
    录
    0.81
    POSITIVE LOGITS
     silicon
    1.27
     magnesium
    1.26
     graphite
    1.24
     potassium
    1.24
     ポリエステル
    1.24
     silicone
    1.23
     aluminio
    1.22
     manganese
    1.19
     aluminum
    1.19
     citrus
    1.19
    Activations Density 1.115%

    No Known Activations