© 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. 108893
    Prev
    Next
    INDEX
    Explanations

    people or relationships

    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
    راس
    -0.92
     strange
    -0.90
     truly
    -0.90
    immutable
    -0.88
     coronel
    -0.86
    戌
    -0.80
     Strawberries
    -0.79
    埤
    -0.79
     Lengkap
    -0.78
     ladr
    -0.77
    POSITIVE LOGITS
    RATIO
    1.03
    犹如
    0.99
     grumpy
    0.86
     parfois
    0.83
     diseños
    0.83
    ANDA
    0.81
     abduction
    0.81
    Parallel
    0.80
     официаль
    0.79
    おば
    0.79
    Activations Density 0.020%

    No Known Activations