© 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. 664
    Prev
    Next
    INDEX
    Explanations

    capital projects and improvement plans

    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
    批量
    -0.74
    orty
    -0.71
     tob
    -0.71
    ox
    -0.71
    AreEqual
    -0.69
    менение
    -0.68
    hibitor
    -0.67
    Albania
    -0.67
    かえ
    -0.66
    グロ
    -0.65
    POSITIVE LOGITS
     gejala
    0.78
    Campaign
    0.69
    คาร
    0.66
    жье
    0.66
    Numerade
    0.65
    COOH
    0.65
    стройство
    0.65
    Launch
    0.64
     לר
    0.64
     forked
    0.64
    Activations Density 0.038%

    No Known Activations