© 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. 84151
    Prev
    Next
    INDEX
    Explanations

    license and terms

    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
    荐
    -0.81
     resur
    -0.77
     ત
    -0.76
     nunca
    -0.75
     resus
    -0.73
     exagger
    -0.72
     puede
    -0.71
     quizás
    -0.70
    También
    -0.69
    طة
    -0.68
    POSITIVE LOGITS
    poses
    0.89
    кета
    0.85
    chende
    0.83
    think
    0.81
     posando
    0.80
    pictured
    0.80
    Inconvénients
    0.80
    bracket
    0.80
     individuell
    0.80
    urther
    0.79
    Activations Density 0.001%

    No Known Activations