© 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. 50305
    Prev
    Next
    INDEX
    Explanations

    ASTM standards and specifications

    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
     Engen
    -0.79
    顆
    -0.75
    Jürgen
    -0.75
     капсу
    -0.75
    principalColumn
    -0.74
     honra
    -0.73
    backButton
    -0.73
    Duración
    -0.72
     tripping
    -0.72
    casual
    -0.71
    POSITIVE LOGITS
     ASTM
    0.94
    AMERICAN
    0.90
     Philadelphia
    0.85
    Annual
    0.84
    Standard
    0.82
     XF
    0.81
     Annual
    0.80
     American
    0.80
    Philadelphia
    0.79
    correre
    0.79
    Activations Density 0.008%

    No Known Activations