© 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. 45253
    Prev
    Next
    INDEX
    Explanations

    code snippets and text headers

    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
     regreso
    -0.84
     всегда
    -0.81
    而成
    -0.80
     pagkak
    -0.80
     tradition
    -0.76
    tradition
    -0.74
    Hochspringen
    -0.73
    camb
    -0.72
    包裝
    -0.71
    ības
    -0.71
    POSITIVE LOGITS
    thanol
    1.03
    随着
    0.97
    urably
    0.96
    numerusform
    0.94
    lably
    0.91
     یو
    0.91
     TabLayout
    0.91
    شنبه
    0.88
     ();
    0.88
     Tarantino
    0.87
    Activations Density 0.000%

    No Known Activations