© 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. 110693
    Prev
    Next
    INDEX
    Explanations

    answering questions, solving conjectures

    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
    MARIA
    -0.82
    }`).
    -0.81
    coltà
    -0.76
     Neander
    -0.76
    izmus
    -0.74
    Mbps
    -0.73
     THURSDAY
    -0.72
     ۳۰
    -0.71
     Nell
    -0.71
     rijk
    -0.71
    POSITIVE LOGITS
     conject
    1.42
     conjecture
    1.34
     conjectures
    1.16
     answering
    1.09
     question
    1.05
    予想
    1.05
    Recently
    1.01
     results
    1.01
     answers
    1.00
     unsolved
    1.00
    Activations Density 0.159%

    No Known Activations