© 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. 7-GEMMASCOPE-2-RES-16K
    7. 554
    Prev
    Next
    INDEX
    Explanations

    God and religion

    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
    𝐧
    1.62
    ፀ
    1.42
    妤
    1.39
    mathml
    1.37
    𝚗
    1.34
     socios
    1.34
     BUREAU
    1.33
    ंसिल
    1.32
    委会
    1.30
    삵
    1.30
    POSITIVE LOGITS
     Christmas
    1.32
    g
    1.32
    ly
    1.31
    ia
    1.30
    edel
    1.29
    ed
    1.28
     adhesive
    1.28
     honoring
    1.25
     Adhesive
    1.23
    ann
    1.21
    Activations Density 0.712%

    No Known Activations