© 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. 20815
    Prev
    Next
    INDEX
    Explanations

    subwoofer system

    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
    哢
    -1.84
    ebly
    -1.84
    “
    -1.83
    pecabe
    -1.81
     deterior
    -1.77
    訁
    -1.73
     ملع
    -1.73
    asında
    -1.70
    gilet
    -1.65
    idk
    -1.64
    POSITIVE LOGITS
    \
    2.05
    𓋼
    1.76
     и
    1.74
    uação
    1.60
     WITH
    1.59
    estones
    1.59
     bauen
    1.57
    
    1.54
    甞
    1.53
    ignment
    1.51
    Activations Density 0.005%

    No Known Activations