© 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. 6318
    Prev
    Next
    INDEX
    Explanations

    base while

    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
    z
    1.36
     màn
    1.25
    ل
    1.22
     sabor
    1.20
     Zasshi
    1.19
     krem
    1.17
    và
    1.16
    تا
    1.16
    وي
    1.15
    ﺎ
    1.15
    POSITIVE LOGITS
    Specification
    1.32
    Descripción
    1.31
    ロマ
    1.20
    নীতিক
    1.19
     disclosing
    1.18
    <blockquote>
    1.17
     revealing
    1.17
    ).”
    1.16
    ETER
    1.16
    を通じて
    1.15
    Activations Density 0.002%

    No Known Activations