© 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. 49443
    Prev
    Next
    INDEX
    Explanations

    Making the

    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
    　「
    -1.02
    　『
    -1.00
    院長
    -0.96
    　※
    -0.95
    　→
    -0.92
     Throughout
    -0.92
     throughout
    -0.92
    　　「
    -0.92
    　↓
    -0.92
     just
    -0.92
    POSITIVE LOGITS
    na
    1.06
     kinda
    1.01
    vi
    0.94
    ga
    0.93
    ne
    0.93
    ra
    0.87
    ay
    0.86
    isPrime
    0.85
     DPA
    0.84
    ce
    0.84
    Activations Density 0.003%

    No Known Activations