© 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. 13241
    Prev
    Next
    INDEX
    Explanations

    followed by descriptive adjectives

    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
     dando
    -2.73
     {
    -2.69
    ৢ
    -2.64
    烀
    -2.63
     принцип
    -2.63
    ↵
    -2.48
    螅
    -2.45
    il
    -2.44
    ଃ
    -2.39
     Ergän
    -2.36
    POSITIVE LOGITS
    饜
    2.92
    という感じ
    2.69
     philosophie
    2.64
    って思
    2.64
    してました
    2.59
     來
    2.52
    って感じ
    2.50
    しちゃ
    2.48
    骈
    2.48
    ！）
    2.42
    Activations Density 0.009%

    No Known Activations