© 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. 34-GEMMASCOPE-RES-131K
    7. 78643
    Prev
    Next
    INDEX
    Explanations

    loop counters or indices

    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
     Belakang
    -0.81
    encodeWith
    -0.79
     bequest
    -0.77
    zonego
    -0.77
    IBM
    -0.77
     risorse
    -0.77
    плек
    -0.75
     الميل
    -0.73
    Сере
    -0.72
     clergyman
    -0.71
    POSITIVE LOGITS
     counter
    4.22
     count
    3.84
    counter
    3.73
    Counter
    3.22
     Counter
    3.19
    count
    3.11
    COUNTER
    3.00
    计数
    2.94
     COUNTER
    2.73
    Count
    2.66
    Activations Density 0.080%

    No Known Activations