© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7059
    Prev
    Next
    INDEX
    Explanations

    providing useful solutions

    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
    auml
    -0.81
    otus
    -0.77
     Encourage
    -0.75
    uminum
    -0.75
     HAZ
    -0.73
    tracer
    -0.73
    loggedin
    -0.70
    øn
    -0.69
     timeType
    -0.68
     زي
    -0.67
    POSITIVE LOGITS
     helpful
    1.55
     providing
    1.50
     useful
    1.49
     solves
    1.43
     value
    1.41
     valuable
    1.41
     solving
    1.40
    提供
    1.38
     provide
    1.33
     solve
    1.33
    Activations Density 0.020%

    No Known Activations