© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73777
    Prev
    Next
    INDEX
    Explanations

    winning and losing streaks

    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
     Clover
    -0.71
     DIAL
    -0.69
     dialing
    -0.67
     couper
    -0.66
    Marion
    -0.66
    Dial
    -0.66
     Switches
    -0.66
     jestem
    -0.66
     Yaman
    -0.66
     Shandong
    -0.65
    POSITIVE LOGITS
     streak
    1.66
     streaks
    1.21
    streak
    1.20
     Streak
    1.05
    Stre
    0.95
     trick
    0.89
     Stre
    0.85
     STRE
    0.82
     habit
    0.79
     tradition
    0.75
    Activations Density 0.040%

    No Known Activations