© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118034
    Prev
    Next
    INDEX
    Explanations

    imgur image links

    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
     symbol
    -0.85
     SPDX
    -0.82
    통
    -0.77
    $\
    -0.76
    symbol
    -0.74
     symbols
    -0.73
    ítica
    -0.73
    ennom
    -0.73
    Ч
    -0.73
    علی
    -0.73
    POSITIVE LOGITS
     Img
    1.60
    imgur
    1.39
     imgur
    1.38
    Imgur
    1.14
     FP
    0.94
     IMG
    0.94
     dump
    0.89
     Dump
    0.86
     Sauce
    0.85
     viñ
    0.85
    Activations Density 0.029%

    No Known Activations