© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8715
    Prev
    Next
    INDEX
    Explanations

    I decided that wanted

    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
     они
    -1.76
     pueden
    -1.64
    vierten
    -1.60
     δύο
    -1.59
    CHOS
    -1.59
     them
    -1.58
    ACZ
    -1.58
    狞
    -1.53
     +'
    -1.53
    chè
    -1.52
    POSITIVE LOGITS
    il
    1.74
    糌
    1.67
     wanted
    1.64
     flesta
    1.52
     that
    1.47
     pomá
    1.47
    鹮
    1.42
     a
    1.41
    わたしは
    1.41
     about
    1.39
    Activations Density 0.029%

    No Known Activations