© 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. 2252
    Prev
    Next
    INDEX
    Explanations

    wikipedia links

    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
    𒁹
    1.60
    ෑම
    1.47
    ENTA
    1.45
     TextEditing
    1.44
    𒈩
    1.42
    ೇವಿನ
    1.42
    র্জেন্ট
    1.42
     proté
    1.41
     puente
    1.39
     logarith
    1.39
    POSITIVE LOGITS
    ​.
    1.43
    当時の
    1.38
    จ
    1.34
     Of
    1.33
    এই
    1.32
       
    1.30
     Research
    1.27
    󠁿
    1.27
    規模
    1.27
    砟
    1.25
    Activations Density 0.115%

    No Known Activations