© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109532
    Prev
    Next
    INDEX
    Explanations

    Wi-Fi

    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
    ghu
    -0.91
     ucapnya
    -0.81
     сказа
    -0.79
    CAUTIONS
    -0.77
    ख़
    -0.76
     Kuh
    -0.76
    两次
    -0.73
    それも
    -0.71
     thrice
    -0.70
    ofil
    -0.70
    POSITIVE LOGITS
     weet
    0.81
     Kendrick
    0.78
    Cast
    0.75
     vitu
    0.75
    successfully
    0.75
     получил
    0.74
     pegatinas
    0.73
    indu
    0.72
     Comunidad
    0.71
    BERTO
    0.71
    Activations Density 0.051%

    No Known Activations