© 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. 58163
    Prev
    Next
    INDEX
    Explanations

    FileReader new BufferedReader

    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
     Nguyên
    -0.87
    aguas
    -0.84
    Apply
    -0.81
    hov
    -0.78
    adag
    -0.77
    泌
    -0.75
    ósitos
    -0.75
    aksikan
    -0.74
    meja
    -0.74
    ưa
    -0.73
    POSITIVE LOGITS
    潺
    0.80
    为例
    0.79
    FileReader
    0.79
    作り方
    0.75
    家乡
    0.75
    enzial
    0.73
    バイオ
    0.73
    ृत
    0.73
    ーン
    0.72
    Aan
    0.72
    Activations Density 0.007%

    No Known Activations