© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 27
    Prev
    Next
    INDEX
    Explanations

    medical advice or substitute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    
    0.27
     benthic
    0.27
     começa
    0.26
     使っ
    0.25
     página
    0.25
     développer
    0.25
     banget
    0.25
     můžete
    0.24
     უფრო
    0.24
     dinosaur
    0.24
    POSITIVE LOGITS
    .
    0.24
    ;
    0.23
    as
    0.22
    with
    0.22
    ,
    0.22
    any
    0.21
    which
    0.21
    is
    0.21
     with
    0.21
    。
    0.21
    Activations Density 0.396%

    No Known Activations