© 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. 90506
    Prev
    Next
    INDEX
    Explanations

    legal documents and formal contexts

    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
    中华
    -0.79
     Drit
    -0.78
     Bemer
    -0.76
    স্ত
    -0.76
    Fortunately
    -0.76
     indor
    -0.76
     AIAA
    -0.74
     einmal
    -0.73
    conector
    -0.73
    üchte
    -0.72
    POSITIVE LOGITS
     ALSO
    1.05
     said
    0.99
     też
    0.97
     evidences
    0.94
    ÓS
    0.90
     also
    0.89
     dimensionless
    0.88
     réservés
    0.87
     essere
    0.86
     również
    0.85
    Activations Density 0.004%

    No Known Activations