© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10117
    Prev
    Next
    INDEX
    Explanations

    ETH to

    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
    琶
    2.43
    竽
    2.23
    Ви
    2.08
    ные
    1.97
    не
    1.96
    舝
    1.94
    agis
    1.94
     secured
    1.92
     признаки
    1.91
    за
    1.89
    POSITIVE LOGITS
    ழுகு
    2.35
    gings
    2.22
    רות
    2.21
    이션
    2.21
    tib
    2.18
    ി
    2.15
    tion
    2.14
    ิ่น
    2.13
    sung
    2.12
    taj
    2.12
    Activations Density 0.085%

    No Known Activations