© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93247
    Prev
    Next
    INDEX
    Explanations

    academic and technical subjects

    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_22/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
     of
    -1.07
    ,
    -1.04
    一样
    -1.02
    useNewUrlParser
    -0.99
     '
    -0.99
    ha
    -0.99
    ￬
    -0.97
    ></
    -0.95
    ться
    -0.91
    wikkeld
    -0.91
    POSITIVE LOGITS
     проє
    1.55
     yüzde
    1.20
    imbangan
    1.08
     ditambah
    1.08
     варіан
    1.06
    の可能性
    1.06
    ográfica
    1.04
     boty
    1.04
     vielfäl
    1.03
     retira
    1.02
    Activations Density 0.050%

    No Known Activations