© 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. 31061
    Prev
    Next
    INDEX
    Explanations

    cellForRow, Red Banner/Star

    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
     TH
    -0.72
    艳
    -0.69
    艷
    -0.68
    Brilliant
    -0.66
     اول
    -0.66
     premiered
    -0.66
     top
    -0.65
    sej
    -0.64
    Uniform
    -0.63
     Lakeland
    -0.63
    POSITIVE LOGITS
    koj
    0.72
    )')
    0.68
     russa
    0.68
     冬
    0.68
    GetData
    0.66
    旃
    0.66
     Pseudo
    0.66
     pseudo
    0.65
    이며
    0.65
    🐽
    0.65
    Activations Density 0.069%

    No Known Activations