© 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. 66087
    Prev
    Next
    INDEX
    Explanations

    calling or called

    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
     apparaissent
    -1.48
     uniquement
    -1.45
     obvio
    -1.44
    裥
    -1.41
     voul
    -1.41
    。"
    -1.41
     maje
    -1.34
    *"
    -1.32
     forment
    -1.30
    饃
    -1.30
    POSITIVE LOGITS
     those
    2.02
     if
    1.98
     new
    1.91
     there
    1.90
     this
    1.84
     when
    1.83
     these
    1.75
     many
    1.71
     after
    1.66
     more
    1.57
    Activations Density 0.093%

    No Known Activations