© 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. 105278
    Prev
    Next
    INDEX
    Explanations

    locations and descriptions

    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
    了不少
    -1.70
    6
    -1.33
     atualmente
    -1.29
     "
    -1.28
    了些
    -1.27
    了好
    -1.27
     garg
    -1.26
    鸲
    -1.21
     própri
    -1.21
    7
    -1.20
    POSITIVE LOGITS
     are
    1.49
     Their
    1.48
     aspects
    1.44
     ersetzen
    1.41
     their
    1.34
     other
    1.33
     There
    1.32
    calça
    1.29
    Perhaps
    1.29
    There
    1.28
    Activations Density 0.004%

    No Known Activations