© 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. 90838
    Prev
    Next
    INDEX
    Explanations

    code artifacts and dates

    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
    HEAP
    -0.83
     its
    -0.81
     évi
    -0.79
    [];
    -0.79
    GRAPHICS
    -0.77
    hana
    -0.76
    〈
    -0.75
     nena
    -0.75
    Then
    -0.73
    Choosing
    -0.73
    POSITIVE LOGITS
     unheard
    0.92
     seeker
    0.82
    Cecil
    0.81
    Kary
    0.80
    iglia
    0.77
     табле
    0.76
    Karol
    0.76
     فلسط
    0.76
    PENG
    0.75
    訳
    0.74
    Activations Density 0.002%

    No Known Activations