© 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. 13832
    Prev
    Next
    INDEX
    Explanations

    damage to entities

    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
    resher
    1.51
     কান
    1.47
    ிர
    1.46
    차가
    1.46
    ractor
    1.41
    ...
    1.40
    차
    1.40
     잡
    1.39
    ันทร์
    1.38
     Tail
    1.35
    POSITIVE LOGITS
    গ্রস্থ
    1.84
     مذہبی
    1.81
     pokud
    1.80
     způso
    1.79
    सामाजिक
    1.71
     ধর্মীয়
    1.68
     iman
    1.62
    spiritual
    1.62
    धारी
    1.62
     clergyman
    1.62
    Activations Density 0.118%

    No Known Activations