© 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. 12160
    Prev
    Next
    INDEX
    Explanations

    freeze or react

    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
    睁开
    -0.85
    зма
    -0.78
     joue
    -0.74
    reihe
    -0.73
     poko
    -0.73
     lasted
    -0.72
     laced
    -0.72
     Maharaj
    -0.71
    tok
    -0.71
    
    -0.71
    POSITIVE LOGITS
     react
    1.22
     froze
    1.19
     freezes
    1.08
     freeze
    1.02
    反應
    1.01
    反应
    0.97
     reacted
    0.94
     frozen
    0.94
     stiff
    0.92
     reaccion
    0.91
    Activations Density 0.004%

    No Known Activations