© 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. 90666
    Prev
    Next
    INDEX
    Explanations

    present study

    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
    癬
    -0.71
    اقل
    -0.66
     packers
    -0.65
    igree
    -0.65
     数字
    -0.64
     ontstaan
    -0.64
     köpek
    -0.63
    shah
    -0.63
    automation
    -0.63
     pedagogy
    -0.62
    POSITIVE LOGITS
    undra
    0.71
     nvm
    0.65
     Reak
    0.64
     Σα
    0.63
     xxii
    0.63
    ajs
    0.62
    行為
    0.61
     bv
    0.60
    yot
    0.60
    ͒
    0.59
    Activations Density 0.109%

    No Known Activations