© 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. 90586
    Prev
    Next
    INDEX
    Explanations

    tokens followed by colon or completion

    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
    Yamaha
    -0.75
    PERMISSION
    -0.75
     |=
    -0.75
     reaksi
    -0.75
     WebView
    -0.72
     californ
    -0.71
    تقاوى
    -0.71
     getResource
    -0.70
     Flach
    -0.70
     vál
    -0.70
    POSITIVE LOGITS
    assertThat
    1.02
     universitarios
    0.84
     beitragen
    0.83
    ductory
    0.81
     erne
    0.78
     다른
    0.78
     teneur
    0.77
    AGAIN
    0.77
     사이
    0.77
    匝
    0.76
    Activations Density 0.000%

    No Known Activations