© 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. 10-GEMMASCOPE-RES-131K
    4. 69185
    Prev
    Next
    INDEX
    Explanations

    only followed by that or which

    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_10/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
     inkább
    -1.75
    ก็
    -1.73
    verstanden
    -1.54
    fotografie
    -1.52
    就是
    -1.47
    machten
    -1.47
     tenues
    -1.44
    خب
    -1.44
    Suomen
    -1.41
    personen
    -1.39
    POSITIVE LOGITS
     of
    1.64
     I
    1.59
     such
    1.55
     we
    1.52
     now
    1.48
    又不是
    1.47
     sees
    1.43
     you
    1.41
     following
    1.37
    &
    
    1.37
    Activations Density 0.029%

    No Known Activations