© 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. 1153
    Prev
    Next
    INDEX
    Explanations

    variations and types

    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
     nhàng
    3.20
    ומי
    3.08
    anées
    2.97
    ுள்ளது
    2.94
    ו
    2.93
    FRAME
    2.88
    y
    2.78
    rable
    2.78
    พาะ
    2.72
     carattere
    2.70
    POSITIVE LOGITS
    нов
    2.34
    ila
    2.16
    polit
    2.10
    istocene
    2.06
    وع
    2.06
    ias
    2.03
    onym
    1.98
    ill
    1.98
    气
    1.96
    illion
    1.96
    Activations Density 0.467%

    No Known Activations