© 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. 127260
    Prev
    Next
    INDEX
    Explanations

    burst into or out of state

    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
    .”
    -2.05
    中国的
    -1.95
    ⢪
    -1.91
    but
    -1.86
     chances
    -1.80
    ⢫
    -1.66
    を変更
    -1.59
     aplicaciones
    -1.55
    C
    -1.54
    ard
    -1.53
    POSITIVE LOGITS
     in
    1.57
     Они
    1.52
    Genero
    1.51
    うちの
    1.50
     mereka
    1.49
    Presidente
    1.45
    鴣
    1.43
     famil
    1.41
     resurrect
    1.40
    ["_
    1.39
    Activations Density 0.010%

    No Known Activations