© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119241
    Prev
    Next
    INDEX
    Explanations

    conditions, training, or questions

    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
     sadly
    -0.92
     però
    -0.91
     but
    -0.87
    ५
    -0.85
     using
    -0.85
     every
    -0.84
    hasia
    -0.83
    !」
    -0.83
     twice
    -0.82
     barely
    -0.82
    POSITIVE LOGITS
    Significant
    1.02
    だったり
    1.01
    requently
    1.01
    )}_
    1.00
     riten
    1.00
     большого
    1.00
    navigationItem
    1.00
    いたり
    1.00
     mojej
    0.99
    significant
    0.98
    Activations Density 0.013%

    No Known Activations