© 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. 82406
    Prev
    Next
    INDEX
    Explanations

    made of or from

    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
    landia
    -0.98
    vich
    -0.95
    𝛾
    -0.95
     prostřed
    -0.92
    structures
    -0.91
     grossa
    -0.90
    icamente
    -0.90
    鵙
    -0.89
    اتب
    -0.89
     делает
    -0.88
    POSITIVE LOGITS
     of
    4.66
     with
    2.03
     from
    1.65
     out
    1.56
     Of
    1.49
     using
    1.36
     из
    1.20
     із
    1.15
    Of
    1.14
    ของ
    1.09
    Activations Density 0.033%

    No Known Activations