© 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. 84999
    Prev
    Next
    INDEX
    Explanations

    rows of

    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
    .
    -1.86
     هناك
    -1.84
    zbęd
    -1.73
    ﹶ
    -1.73
     dni
    -1.72
     недавно
    -1.71
    𞤭
    -1.70
    侑
    -1.68
    تیجه
    -1.66
    eseorang
    -1.65
    POSITIVE LOGITS
    ar
    2.17
    c
    2.05
    i
    1.88
     '
    1.80
    你来
    1.79
    ia
    1.78
     the
    1.75
    𝑥
    1.73
    I
    1.71
    al
    1.70
    Activations Density 0.026%

    No Known Activations