© 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. 33057
    Prev
    Next
    INDEX
    Explanations

    can be or may be

    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
     probably
    -1.17
     which
    -1.14
     will
    -0.95
    }^{-
    -0.91
     get
    -0.91
     Probably
    -0.90
     all
    -0.90
     вероятно
    -0.90
     at
    -0.89
     should
    -0.87
    POSITIVE LOGITS
     either
    2.16
    either
    1.92
     be
    1.81
    Either
    1.70
     berupa
    1.68
     range
    1.53
     entweder
    1.50
    Takes
    1.49
     любого
    1.43
     anywhere
    1.37
    Activations Density 0.100%

    No Known Activations