© 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. 105676
    Prev
    Next
    INDEX
    Explanations

    nothing to do with

    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
    莛
    -1.96
    茕
    -1.75
    derdag
    -1.74
    viève
    -1.66
    ocats
    -1.62
    ⡦
    -1.59
    ers
    -1.59
    🫃
    -1.59
     ”
    -1.57
     perpé
    -1.57
    POSITIVE LOGITS
     you
    1.57
    2
    1.54
    it
    1.51
    的事情
    1.47
     آنان
    1.46
     that
    1.45
    成立
    1.45
     Entste
    1.44
     mendatang
    1.43
    ্ড
    1.43
    Activations Density 0.004%

    No Known Activations