© 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. 59386
    Prev
    Next
    INDEX
    Explanations

    dealing with it or discussion

    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
    🍙
    -0.91
    曲を
    -0.84
     various
    -0.79
     Eigentü
    -0.79
    aqua
    -0.76
    澗
    -0.75
    らかに
    -0.74
     nena
    -0.74
     Praying
    -0.74
    مام
    -0.73
    POSITIVE LOGITS
     trata
    3.47
     handelt
    3.08
     речь
    2.61
     chodzi
    2.31
     it
    2.23
     tratta
    2.22
     treated
    1.82
     treat
    1.80
    treat
    1.77
    Treat
    1.72
    Activations Density 0.010%

    No Known Activations