© 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. 9107
    Prev
    Next
    INDEX
    Explanations

    protection for, from, against

    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
    دود
    -1.56
    』(
    -1.46
    >
    -1.45
     intricate
    -1.41
    følgelig
    -1.40
    ꯶
    -1.37
     ночью
    -1.36
    ásticas
    -1.34
    (
    -1.34
    珢
    -1.33
    POSITIVE LOGITS
     of
    2.09
     against
    1.77
    鲩
    1.69
     beziehungs
    1.45
     côn
    1.37
    行きます
    1.35
    ização
    1.35
     dando
    1.34
    だけでなく
    1.34
     durante
    1.33
    Activations Density 0.034%

    No Known Activations