© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67781
    Prev
    Next
    INDEX
    Explanations

    solve math problems

    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_10/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
     principalmente
    -1.88
     нашего
    -1.67
     małe
    -1.65
     нашей
    -1.59
     naszej
    -1.55
     principalement
    -1.54
     ſe
    -1.51
    ANGAN
    -1.50
     eminent
    -1.48
     naszego
    -1.45
    POSITIVE LOGITS
     these
    2.02
     will
    1.91
     those
    1.69
     băr
    1.55
     at
    1.52
    шего
    1.51
     with
    1.49
     would
    1.41
     during
    1.39
    はこんな感じ
    1.39
    Activations Density 0.002%

    No Known Activations