© 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. 34-GEMMASCOPE-RES-131K
    7. 45593
    Prev
    Next
    INDEX
    Explanations

    JLT, dubai, marina, palm

    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
    资质
    -0.73
    ässig
    -0.70
     ред
    -0.70
     години
    -0.66
     []:
    -0.65
     truest
    -0.65
    🔢
    -0.64
     Rebels
    -0.63
    ਅ
    -0.63
    recv
    -0.62
    POSITIVE LOGITS
     Palm
    1.21
    Palm
    1.07
     Jume
    0.96
     archipelago
    0.94
    Analyst
    0.84
    palm
    0.83
    shaped
    0.82
    island
    0.82
     island
    0.82
     dubai
    0.81
    Activations Density 0.019%

    No Known Activations