© 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. 90568
    Prev
    Next
    INDEX
    Explanations

    protect from harm

    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
    すぎて
    -1.04
    ったので
    -1.01
    ijnlijk
    -0.96
     geringer
    -0.96
    庭園
    -0.94
    几个人
    -0.92
     winners
    -0.92
     varones
    -0.91
    rror
    -0.90
    と言って
    -0.88
    POSITIVE LOGITS
     being
    2.08
     becoming
    1.91
     any
    1.45
    becoming
    1.37
    来自
    1.37
     harm
    1.30
    Becoming
    1.25
     menjadi
    1.24
     having
    1.23
    ització
    1.23
    Activations Density 0.057%

    No Known Activations