© 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. 73621
    Prev
    Next
    INDEX
    Explanations

    seeking new ways or methods

    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
    ussch
    -1.02
    τική
    -0.95
    keth
    -0.92
    taires
    -0.92
    нале
    -0.90
    τια
    -0.89
    astia
    -0.89
    phora
    -0.89
    nitř
    -0.87
    攔
    -0.86
    POSITIVE LOGITS
     ways
    7.13
    Ways
    4.44
     Ways
    4.19
    ways
    3.59
     methods
    3.41
     way
    3.39
     WAYS
    3.36
     спосо
    2.89
     strategies
    2.83
    WAYS
    2.70
    Activations Density 0.256%

    No Known Activations