© 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. 58809
    Prev
    Next
    INDEX
    Explanations

    sameness or difference between entities

    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
     itself
    -1.04
     its
    -0.99
    集体
    -0.93
     also
    -0.91
     мень
    -0.89
    它的
    -0.89
     colectivo
    -0.86
     collectif
    -0.85
     Collective
    -0.84
    与
    -0.83
    POSITIVE LOGITS
     birbir
    1.46
     saling
    1.35
     mutually
    1.19
    互
    1.18
     alike
    1.16
     서
    1.14
     elkaar
    1.13
     complementary
    1.13
     einander
    1.05
     separated
    1.04
    Activations Density 0.132%

    No Known Activations