© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2005
    Prev
    Next
    INDEX
    Explanations

    mayoclinic.org/diseases-conditions/

    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
     approximation
    1.79
    igma
    1.70
    FragmentManager
    1.65
    禺
    1.60
     judgement
    1.58
     analogy
    1.57
     authorisation
    1.55
     brake
    1.55
     inconclusive
    1.55
     unwise
    1.54
    POSITIVE LOGITS
    ي
    1.94
    िस्ट
    1.70
    <%=
    1.68
    วัสดี
    1.62
     facilité
    1.58
    Shoes
    1.58
    览
    1.57
    polit
    1.57
     Teilnahme
    1.57
    étés
    1.56
    Activations Density 0.217%

    No Known Activations