© 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. 83999
    Prev
    Next
    INDEX
    Explanations

    cross, crossed, crosses

    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
    情人
    -0.92
    Objects
    -0.89
    Values
    -0.79
     values
    -0.79
    atorul
    -0.78
    花
    -0.78
    更
    -0.77
    VALUE
    -0.76
    String
    -0.76
    value
    -0.75
    POSITIVE LOGITS
    anonymous
    1.04
     anonymous
    0.92
    Bamb
    0.91
      (
    0.89
     crosses
    0.89
     Cross
    0.88
     cross
    0.88
    Epil
    0.87
     crossed
    0.84
     crossbow
    0.84
    Activations Density 0.004%

    No Known Activations