© 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. 10-GEMMASCOPE-RES-131K
    7. 47854
    Prev
    Next
    INDEX
    Explanations

    Santa Barbara, secrets, or databases

    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
    咵
    -3.34
    ものに
    -3.06
     exceptionally
    -3.05
    z
    -2.92
    もの
    -2.86
     ridiculously
    -2.83
    io
    -2.78
    r
    -2.72
    ം
    -2.72
     ludicrous
    -2.61
    POSITIVE LOGITS
    ⁍
    2.84
    韞
    2.63
    ſelves
    2.59
     bekämp
    2.48
     If
    2.45
     When
    2.39
     Füße
    2.36
    房間
    2.36
    BIÉN
    2.34
    ни
    2.31
    Activations Density 0.001%

    No Known Activations