© 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. 45299
    Prev
    Next
    INDEX
    Explanations

    direction and distance

    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
    齣
    -0.84
     Türen
    -0.82
    lr
    -0.78
    down
    -0.78
    bujete
    -0.78
     pastures
    -0.77
    どん
    -0.77
     объекта
    -0.75
    meyen
    -0.75
     çı
    -0.75
    POSITIVE LOGITS
     the
    2.33
     into
    1.27
     through
    1.18
     to
    1.15
     from
    0.92
     towards
    0.91
     toward
    0.89
    river
    0.86
     가장
    0.85
    ~~~~~~~~~~~~~~~~
    0.82
    Activations Density 0.017%

    No Known Activations