© 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. 49638
    Prev
    Next
    INDEX
    Explanations

    evaluating mathematical expressions

    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
     Ferrara
    -0.83
     poética
    -0.78
    aib
    -0.77
    lcm
    -0.77
     スウェット
    -0.77
    
    -0.76
    dP
    -0.76
    łop
    -0.74
    ્
    -0.74
     côté
    -0.73
    POSITIVE LOGITS
     evaluation
    2.75
     evaluated
    2.63
     evaluations
    2.61
     evaluate
    2.52
     evaluates
    2.39
     evaluating
    2.38
     value
    2.38
     Evaluation
    2.31
    Evaluation
    2.25
     eval
    2.22
    Activations Density 0.099%

    No Known Activations