© 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. 12515
    Prev
    Next
    INDEX
    Explanations

    rights and opinions

    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
    𝘶
    2.59
    עים
    2.52
    
    2.50
    ᆯ
    2.48
    砰
    2.40
    Sean
    2.38
    пі
    2.37
    hashTree
    2.36
    gle
    2.35
    LLOW
    2.32
    POSITIVE LOGITS
    ের
    2.87
    는지
    2.75
    ों
    2.68
    ೋತಿ
    2.34
    ׁ
    2.25
    ︎
    2.24
    கிழ
    2.23
    ्ट
    2.23
     untimely
    2.21
     soát
    2.19
    Activations Density 0.033%

    No Known Activations