© 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. 38415
    Prev
    Next
    INDEX
    Explanations

    version and license

    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
     Zufall
    -0.84
    лочка
    -0.84
    riturismo
    -0.81
     tangerang
    -0.80
    حدى
    -0.80
     günstig
    -0.79
     avevo
    -0.78
    capace
    -0.77
    ेश
    -0.77
    POSITIVE LOGITS
     Module
    0.99
    forRoot
    0.98
    Module
    0.87
     disse
    0.83
     importing
    0.83
     module
    0.81
     MODULE
    0.78
    ]]>
    0.77
     modules
    0.76
     Mó
    0.76
    Activations Density 0.004%

    No Known Activations