© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57906
    Prev
    Next
    INDEX
    Explanations

    save, restore, original, backup

    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
    打量
    -0.81
    最新的
    -0.73
    receita
    -0.71
     Tieren
    -0.71
    禮物
    -0.69
    你們
    -0.69
     emerging
    -0.69
    Ops
    -0.68
    Akhir
    -0.68
    するという
    -0.68
    POSITIVE LOGITS
     original
    2.44
     backup
    2.25
     saved
    2.17
    backup
    2.09
    original
    2.09
     save
    2.02
     old
    1.94
    saved
    1.85
     temporarily
    1.83
    ORIGINAL
    1.83
    Activations Density 0.020%

    No Known Activations