© 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. 75822
    Prev
    Next
    INDEX
    Explanations

    file license

    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
     canta
    -1.00
    スピード
    -0.82
     childbirth
    -0.79
    EDY
    -0.79
    ocracy
    -0.77
     nasel
    -0.76
    娠
    -0.75
     ramai
    -0.75
    quoi
    -0.74
     rač
    -0.74
    POSITIVE LOGITS
    ⌄
    0.93
    ју
    0.84
    々は
    0.81
    넓
    0.81
     是否
    0.77
    CG
    0.75
     فی
    0.74
    blé
    0.73
    lsp
    0.73
     purchased
    0.71
    Activations Density 0.060%

    No Known Activations