© 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. 107232
    Prev
    Next
    INDEX
    Explanations

    electrical transmission circuits

    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
    ภาษา
    -0.73
    гиоз
    -0.73
    kolan
    -0.71
    Verwaltung
    -0.71
     машины
    -0.71
    ί
    -0.68
     сосу
    -0.68
    幕
    -0.68
     linearly
    -0.67
     colonel
    -0.67
    POSITIVE LOGITS
     ABCD
    1.11
    ABCD
    0.90
     Scattering
    0.83
     NRW
    0.81
     Yahya
    0.80
     scattering
    0.77
    decap
    0.76
    ござ
    0.75
     Network
    0.74
     Networks
    0.73
    Activations Density 0.025%

    No Known Activations