© 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. 56022
    Prev
    Next
    INDEX
    Explanations

    arithmetic puzzle

    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
     akan
    -0.80
     APR
    -0.75
     practi
    -0.75
    tamin
    -0.74
    risti
    -0.72
     their
    -0.72
    Rohit
    -0.71
     this
    -0.71
    ɬ
    -0.70
    назна
    -0.70
    POSITIVE LOGITS
    πάρχ
    1.03
     legge
    0.81
    batore
    0.79
    óp
    0.79
    onNext
    0.78
    Ӳ
    0.78
     targ
    0.77
    Onder
    0.77
     Wolfs
    0.77
     asemenea
    0.76
    Activations Density 0.001%

    No Known Activations