© 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. 102374
    Prev
    Next
    INDEX
    Explanations

    ranges from to

    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
    کین
    -0.93
    obel
    -0.87
    broj
    -0.86
     بیمارستان
    -0.83
    首先
    -0.82
    Та
    -0.81
    Ẓ
    -0.81
    Тай
    -0.81
     putea
    -0.80
    setminus
    -0.80
    POSITIVE LOGITS
     between
    2.09
     from
    2.05
    between
    1.18
     ampliamente
    1.15
     zwischen
    1.08
     medzi
    1.08
     между
    1.04
     بين
    1.03
     widely
    1.02
     among
    0.96
    Activations Density 0.021%

    No Known Activations