© 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. 7064
    Prev
    Next
    INDEX
    Explanations

    physical components and parts

    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
    الحياه
    -0.89
    Jap
    -0.79
     Auflösung
    -0.79
    шайте
    -0.79
    라는
    -0.77
    
    -0.77
    грамма
    -0.76
     Jap
    -0.76
    rosos
    -0.75
    viä
    -0.75
    POSITIVE LOGITS
     type
    1.13
     types
    0.93
    Quercus
    0.88
     storing
    0.87
     pagkak
    0.86
    PARTITION
    0.85
     TYPE
    0.85
     valsty
    0.83
     PET
    0.81
     prevents
    0.81
    Activations Density 0.227%

    No Known Activations