© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116180
    Prev
    Next
    INDEX
    Explanations

    code and scientific descriptions

    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
     conséquences
    -0.79
    <0x8A>
    -0.74
    ሱ
    -0.72
    شاه
    -0.71
    aspir
    -0.70
    materi
    -0.69
    ratulations
    -0.69
    dańsk
    -0.69
    Fé
    -0.69
    <0xE0>
    -0.68
    POSITIVE LOGITS
    structions
    0.65
    ury
    0.65
    works
    0.64
     Neumann
    0.64
    naie
    0.63
    rollup
    0.63
     impro
    0.63
    ick
    0.62
     сверху
    0.62
     Robertson
    0.62
    Activations Density 0.074%

    No Known Activations