© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62858
    Prev
    Next
    INDEX
    Explanations

    words starting with pre

    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
     although
    -0.76
    。　　
    -0.75
    たり
    -0.75
    柘
    -0.74
    ثمان
    -0.73
     rookies
    -0.73
    zlo
    -0.72
    講座
    -0.71
    CST
    -0.71
    quias
    -0.71
    POSITIVE LOGITS
    を探す
    0.97
    ほら
    0.90
     cordón
    0.89
     cordones
    0.88
    Omg
    0.87
    んですよ
    0.86
     residentes
    0.84
    knew
    0.84
    えっ
    0.83
     consommer
    0.83
    Activations Density 0.041%

    No Known Activations