© 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. 34-GEMMASCOPE-RES-131K
    7. 65220
    Prev
    Next
    INDEX
    Explanations

    synergistic

    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_34/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
    ু
    -0.91
    használ
    -0.77
     quirk
    -0.72
    ných
    -0.71
    ném
    -0.70
     poorly
    -0.70
    riturismo
    -0.70
    ೆ
    -0.69
    بيع
    -0.69
    父親
    -0.69
    POSITIVE LOGITS
    ip
    1.27
    ʻ
    1.10
    gin
    1.09
    gy
    1.05
    eare
    1.02
    ea
    1.00
    gins
    0.98
    ach
    0.98
    ote
    0.98
    ell
    0.97
    Activations Density 0.192%

    No Known Activations