© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32062
    Prev
    Next
    INDEX
    Explanations

    fresh start

    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
     agregar
    -0.82
     badkamer
    -0.78
    转化
    -0.73
    τρι
    -0.72
    juga
    -0.72
     pymysql
    -0.72
    diğini
    -0.71
     verv
    -0.71
     heapq
    -0.71
    niet
    -0.70
    POSITIVE LOGITS
     fresh
    4.66
    fresh
    3.84
    Fresh
    3.45
     Fresh
    3.41
     FRESH
    2.75
     afresh
    2.52
    FRESH
    2.44
     start
    2.30
     freshness
    2.28
     restart
    2.16
    Activations Density 0.037%

    No Known Activations