© 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. 3057
    Prev
    Next
    INDEX
    Explanations

    competition advantage and analysis

    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
    γγελ
    2.38
    لا
    2.35
    룬
    2.32
    ੲ
    2.29
    รรม
    2.26
    렬
    2.26
    베
    2.21
     되지
    2.21
     سمت
    2.20
    ਲਾ
    2.18
    POSITIVE LOGITS
    ্ঠ
    2.88
     InputListener
    2.75
    onate
    2.70
    taining
    2.53
    dehyde
    2.51
    tains
    2.49
    oq
    2.48
     remedy
    2.44
    arence
    2.43
     почи
    2.43
    Activations Density 0.085%

    No Known Activations