© 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. 1619
    Prev
    Next
    INDEX
    Explanations

    numbered lists and classifications

    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
    栆
    2.52
    婹
    2.48
    motionProxy
    2.45
    侢
    2.37
     grundsätzlich
    2.26
    攺
    2.22
    騏
    2.22
    亽
    2.19
     musí
    2.18
    朩
    2.18
    POSITIVE LOGITS
    3.06
    1
    2.34
    2
    2.03
     II
    1.94
     III
    1.86
    7
    1.70
    6
    1.69
     £
    1.68
     B
    1.67
     No
    1.67
    Activations Density 0.559%

    No Known Activations