© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1896
    Prev
    Next
    INDEX
    Explanations

    street names and types

    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_7_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
    Ⓜ
    1.95
     Zentr
    1.86
    imetro
    1.85
    centrum
    1.84
    شك
    1.82
    🚕
    1.82
    बादी
    1.82
    ärte
    1.81
    ätzlich
    1.80
    नाल्ड
    1.80
    POSITIVE LOGITS
    子
    1.77
    子的
    1.76
     initially
    1.64
     子
    1.62
    keeper
    1.59
     Jr
    1.57
     would
    1.56
     II
    1.50
    cake
    1.47
     Sr
    1.47
    Activations Density 0.240%

    No Known Activations