© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8777
    Prev
    Next
    INDEX
    Explanations

    health professional

    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_13_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
    oretically
    1.22
    ↵
    1.15
     postpone
    1.11
     unpleasant
    1.10
     great
    1.09
     obvious
    1.08
     excuse
    1.05
     terrible
    1.03
     darn
    1.02
     believe
    1.01
    POSITIVE LOGITS
     também
    1.63
    .].
    1.61
     همچنین
    1.61
     أيضًا
    1.60
     Ayrıca
    1.60
     també
    1.59
     también
    1.59
     ayrıca
    1.59
     asimismo
    1.58
     također
    1.55
    Activations Density 0.110%

    No Known Activations