© 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. 99283
    Prev
    Next
    INDEX
    Explanations

    however with objective order

    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
     .........
    -0.92
    ..............
    -0.83
     ober
    -0.80
    鋁
    -0.80
     .............
    -0.79
    .........
    -0.77
     ito
    -0.77
    ₩
    -0.77
     ..........
    -0.77
     ..............
    -0.77
    POSITIVE LOGITS
    クサ
    0.88
    řevě
    0.85
     Linea
    0.83
     Վեր
    0.82
     érté
    0.82
     dekoratif
    0.81
    tował
    0.81
    zesse
    0.79
    Elevator
    0.79
     solidified
    0.78
    Activations Density 0.010%

    No Known Activations