© 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. 13996
    Prev
    Next
    INDEX
    Explanations

    three types or sections

    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
    imageList
    2.55
     Lose
    2.45
     Stay
    2.44
     elevate
    2.26
     Go
    2.21
     l
    2.11
     die
    2.09
    ו
    2.08
    기
    2.06
    Stay
    2.05
    POSITIVE LOGITS
     (_.
    3.03
     భాగంగా
    2.96
    此同时
    2.95
    াকুর
    2.86
    忡
    2.72
    ksen
    2.71
    iejsc
    2.69
    yland
    2.69
    躇
    2.68
    سٹم
    2.66
    Activations Density 0.035%

    No Known Activations