© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77266
    Prev
    Next
    INDEX
    Explanations

    DIY projects and technology names

    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
     nominal
    -0.80
     individual
    -0.77
    ENNIS
    -0.75
     Seas
    -0.74
    altar
    -0.73
    mondo
    -0.72
    indiri
    -0.72
    گه
    -0.71
    вић
    -0.70
     layak
    -0.69
    POSITIVE LOGITS
    pm
    1.29
     området
    0.94
     condiv
    0.88
    PM
    0.85
    INE
    0.82
     chrétienne
    0.81
    Packages
    0.79
    Share
    0.77
     Rui
    0.76
     Nuevas
    0.76
    Activations Density 0.001%

    No Known Activations