© 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. 10-GEMMASCOPE-RES-131K
    7. 48402
    Prev
    Next
    INDEX
    Explanations

    programming module definitions

    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
    -1.91
    FundMe
    -1.66
    。
    -1.59
    neling
    -1.59
     They
    -1.57
     them
    -1.55
    ini
    -1.51
    tivities
    -1.41
    ciles
    -1.41
    就跟
    -1.39
    POSITIVE LOGITS
    如果您
    1.59
    如果你
    1.59
    如果
    1.55
     ответствен
    1.52
    Shortly
    1.47
     評価
    1.45
    Jika
    1.45
    Après
    1.41
     llevando
    1.41
    acağ
    1.39
    Activations Density 0.001%

    No Known Activations