© 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. 91087
    Prev
    Next
    INDEX
    Explanations

    phase transition

    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
    viar
    -0.70
    长得
    -0.70
    PRACT
    -0.70
    Masters
    -0.69
     Masters
    -0.69
    Compos
    -0.68
     pengar
    -0.66
    urger
    -0.66
     Tzu
    -0.65
    ituksen
    -0.65
    POSITIVE LOGITS
     phase
    4.88
    phase
    4.00
    Phase
    3.97
     Phase
    3.95
     PHASE
    3.25
    PHASE
    3.02
     phases
    2.95
     fase
    2.45
     Phases
    2.31
    phases
    2.27
    Activations Density 0.091%

    No Known Activations