© 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. 60101
    Prev
    Next
    INDEX
    Explanations

    super calling methods

    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
     enchufe
    -0.91
    Répondre
    -0.85
    
    -0.84
    hild
    -0.82
    艘
    -0.79
     pracovní
    -0.78
    ruka
    -0.77
    oer
    -0.77
     Pumps
    -0.77
    maining
    -0.77
    POSITIVE LOGITS
     will
    0.96
    дован
    0.90
    common
    0.82
    دانلود
    0.82
     卧室
    0.78
     покра
    0.74
     corrector
    0.74
    現代
    0.72
     common
    0.71
    );
    0.71
    Activations Density 0.005%

    No Known Activations