© 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. 87107
    Prev
    Next
    INDEX
    Explanations

    data access layer

    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
    During
    -1.91
    This
    -1.88
    Today
    -1.73
    With
    -1.69
    Until
    -1.61
    Since
    -1.61
    Because
    -1.61
    Unlike
    -1.60
    Through
    -1.60
    From
    -1.59
    POSITIVE LOGITS
    kében
    1.43
     we
    1.36
    pci
    1.31
    dhan
    1.31
    </h4>
    1.28
    ":{
    1.23
    HCM
    1.22
    
    1.20
    stücke
    1.19
    siv
    1.18
    Activations Density 0.029%

    No Known Activations