© 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. 1114
    Prev
    Next
    INDEX
    Explanations

    marketed, prove, dissimilar, kan

    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
    Наводи
    -0.88
     температуре
    -0.87
    naux
    -0.86
     cargar
    -0.85
     BRAZIL
    -0.85
    ＊＊
    -0.84
    vedev
    -0.82
    coer
    -0.82
    這位
    -0.82
     preta
    -0.82
    POSITIVE LOGITS
    kan
    1.73
    ankan
    0.90
    KAN
    0.86
     dissimilar
    0.82
    volve
    0.79
     laiton
    0.77
    ken
    0.76
     Sitten
    0.76
    鏽
    0.75
     nieuw
    0.74
    Activations Density 0.001%

    No Known Activations