© 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. 14810
    Prev
    Next
    INDEX
    Explanations

    sports and activities

    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
    𝚖
    2.19
    𝚕
    2.18
    𝚛
    2.02
    𝚜
    2.01
    𝚝
    1.90
    pir
    1.88
    ्रेडिट
    1.84
    κι
    1.82
    ئی
    1.80
    liegt
    1.80
    POSITIVE LOGITS
    ו
    2.68
    يجي
    2.59
    髏
    2.53
    י
    2.50
    ي
    2.43
    oncé
    2.43
    sley
    2.42
    asie
    2.42
    𝙖
    2.41
    renergic
    2.40
    Activations Density 0.243%

    No Known Activations