© 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. 2947
    Prev
    Next
    INDEX
    Explanations

    Themanynumerousa fewbuildingManymassivecapitalthosemodern

    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
     "¿
    1.65
     設計
    1.65
     事業
    1.63
    ันทร์
    1.62
    ารย์
    1.59
    Bibliographie
    1.59
    getItems
    1.59
    鏉
    1.56
     Redeemer
    1.55
     Володимир
    1.54
    POSITIVE LOGITS
    leriyle
    1.29
     combina
    1.28
    stu
    1.15
    lis
    1.11
    lerine
    1.11
    stering
    1.10
    ching
    1.09
    lu
    1.09
    ruct
    1.07
    l
    1.06
    Activations Density 0.266%

    No Known Activations