© 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. 112285
    Prev
    Next
    INDEX
    Explanations

    sequence of zeros

    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
     démocr
    -1.81
    籥
    -1.76
    之类的
    -1.75
    出来的
    -1.73
    慥
    -1.71
     godziny
    -1.69
     incred
    -1.67
     certaines
    -1.63
     voila
    -1.60
    了什么
    -1.58
    POSITIVE LOGITS
     permettra
    1.94
     it
    1.93
    "،
    1.92
    𖥧
    1.77
    ”（
    1.63
    虽
    1.63
    部长
    1.63
    柃
    1.62
    )”
    1.62
     With
    1.61
    Activations Density 0.008%

    No Known Activations