© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 626
    Prev
    Next
    INDEX
    Explanations

    deep flexion

    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
    quierda
    -0.77
     raging
    -0.72
    ieden
    -0.71
    脍
    -0.71
    short
    -0.70
    zeni
    -0.69
     short
    -0.69
    magini
    -0.68
     aufgehoben
    -0.66
    aspectRatio
    -0.65
    POSITIVE LOGITS
     depth
    1.87
    Depth
    1.68
    depth
    1.67
     Depth
    1.66
     deepest
    1.63
     squat
    1.52
     deep
    1.45
     depths
    1.42
     deeper
    1.40
    深度
    1.37
    Activations Density 0.020%

    No Known Activations