© 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. 14585
    Prev
    Next
    INDEX
    Explanations

    difference between

    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
    1.89
    3
    1.73
    2
    1.70
    7
    1.57
    4
    1.53
    6
    1.50
    9
    1.50
    5
    1.46
    8
    1.39
    1.38
    POSITIVE LOGITS
    冽
    1.96
     என்கிற
    1.91
    伲
    1.91
    梔
    1.83
     récol
    1.83
    ಬೇವಿನ
    1.82
    テント
    1.81
    iciaire
    1.81
     banderas
    1.81
     dokt
    1.78
    Activations Density 0.003%

    No Known Activations