© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9555
    Prev
    Next
    INDEX
    Explanations

    operating system, version control

    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_22_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
     Shape
    1.21
     shape
    1.19
     suitability
    1.07
    。
    1.07
     Stuff
    1.02
     inclusive
    1.01
     applicability
    1.01
     DAV
    1.00
     Inclusive
    1.00
     reliable
    1.00
    POSITIVE LOGITS
    적으로
    1.94
    적인
    1.91
    적
    1.58
    ական
    1.41
    的には
    1.40
    的に
    1.38
    성의
    1.35
    的な
    1.34
    性的
    1.31
    적이
    1.31
    Activations Density 0.012%

    No Known Activations