© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11930
    Prev
    Next
    INDEX
    Explanations

    quotation or invoice text

    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
    dbp
    1.94
    ပိုင်း
    1.85
    뚱
    1.65
    っき
    1.60
    finn
    1.59
    scn
    1.58
    freund
    1.57
    চ্ছিলেন
    1.57
    삐
    1.56
    굵
    1.55
    POSITIVE LOGITS
     insecticides
    2.35
     fungicides
    2.31
     sprayed
    2.29
    ilent
    2.27
     spray
    2.24
     glyphosate
    2.23
     ordnance
    2.23
     shipment
    2.18
     sprays
    2.16
    套装
    2.16
    Activations Density 0.144%

    No Known Activations