© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86629
    Prev
    Next
    INDEX
    Explanations

    programming object instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    および
    -1.14
     zawsze
    -1.11
     and
    -1.11
    包裝
    -1.07
     including
    -1.05
    ro
    -1.03
     at
    -1.03
    Composición
    -1.02
     verschieden
    -0.98
     my
    -0.98
    POSITIVE LOGITS
    HideInInspector
    1.22
     kré
    1.21
    {
    1.20
    prettier
    1.19
     године
    1.18
    鯡
    1.15
    $("
    1.14
    ɀ
    1.14
    伎
    1.14
     influenci
    1.13
    Activations Density 0.055%

    No Known Activations