© 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. 84980
    Prev
    Next
    INDEX
    Explanations

    getIntent, Bundle, intent

    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
     capitan
    -0.82
     marco
    -0.81
     falsa
    -0.79
     misericordia
    -0.79
     conster
    -0.78
     trofeo
    -0.78
    Besitos
    -0.77
    Filmo
    -0.77
    Cevap
    -0.77
     ferons
    -0.77
    POSITIVE LOGITS
     getIntent
    2.14
    Bundle
    1.88
    getIntent
    1.71
     intent
    1.54
    Intent
    1.50
     intention
    1.42
     Bundle
    1.36
     intended
    1.33
     bundle
    1.32
     Intent
    1.31
    Activations Density 0.010%

    No Known Activations