© 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. 1567
    Prev
    Next
    INDEX
    Explanations

    addressing problems

    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
    综
    2.97
    𝑬
    2.96
    ਿਆ
    2.50
    Ed
    2.48
    upi
    2.46
    ets
    2.44
    ++
    2.44
    PickerController
    2.42
    ئی
    2.40
    ⊇
    2.37
    POSITIVE LOGITS
    e
    4.59
    ০
    4.51
    tive
    4.50
    ી
    4.45
    eer
    4.40
    eel
    4.29
    ी
    4.19
    י
    4.09
    eurs
    4.07
    ele
    4.05
    Activations Density 0.571%

    No Known Activations