© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 61122
    Prev
    Next
    INDEX
    Explanations

    spatial locations

    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
     and
    -1.55
    now
    -1.52
    ти
    -1.47
     Now
    -1.40
     verho
    -1.37
    い
    -1.34
    ynek
    -1.34
    chauen
    -1.32
    .
    -1.32
    用于
    -1.31
    POSITIVE LOGITS
    olesome
    1.66
    分区
    1.57
     überprü
    1.55
    捱
    1.53
     всех
    1.45
     "]";
    1.43
     jsme
    1.42
    </h4>
    1.42
     sicheren
    1.42
     gleichen
    1.41
    Activations Density 0.044%

    No Known Activations