© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82325
    Prev
    Next
    INDEX
    Explanations

    css display block

    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_34/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
     déjà
    -1.00
     TRAIN
    -0.98
    ikasi
    -0.94
     dấu
    -0.94
     Româ
    -0.93
    霈
    -0.92
    fifty
    -0.90
    pantalones
    -0.89
    jalan
    -0.89
     katt
    -0.89
    POSITIVE LOGITS
     with
    0.78
     their
    0.76
     again
    0.74
    家主
    0.74
     vital
    0.73
     הז
    0.73
     width
    0.72
     white
    0.72
    graves
    0.72
     cha
    0.71
    Activations Density 0.011%

    No Known Activations