© 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. 22-GEMMASCOPE-RES-131K
    4. 68435
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations and counting

    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_22/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
     otros
    -0.94
    otros
    -0.87
    וּ
    -0.86
    Ҳ
    -0.85
    ᕦ
    -0.84
     memulai
    -0.84
    ierend
    -0.84
    telijke
    -0.84
     stolet
    -0.82
    Étienne
    -0.82
    POSITIVE LOGITS
     очеред
    0.84
    mahan
    0.83
     Stufe
    0.81
    监
    0.80
    POP
    0.79
    次
    0.79
     увеличи
    0.79
     new
    0.78
    ineries
    0.78
     meaningless
    0.77
    Activations Density 0.021%

    No Known Activations