© 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. 93637
    Prev
    Next
    INDEX
    Explanations

    in development or construction

    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
     forhold
    -0.92
    今回の
    -0.77
    forhold
    -0.71
     READING
    -0.70
    ünsche
    -0.69
    レシピ
    -0.68
    멜
    -0.68
    METHODS
    -0.68
    コード
    -0.68
     område
    -0.68
    POSITIVE LOGITS
     process
    2.45
     progress
    2.22
     proceso
    1.80
    process
    1.72
     development
    1.67
     underway
    1.52
    progress
    1.47
     construction
    1.43
     production
    1.41
     preparation
    1.37
    Activations Density 0.046%

    No Known Activations