© 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. 11930
    Prev
    Next
    INDEX
    Explanations

    crossing and movement

    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
    zole
    -0.75
    Boas
    -0.71
    واف
    -0.68
     Stimmen
    -0.67
    unked
    -0.66
    🤒
    -0.66
     Compatibility
    -0.65
    XmlAccessorType
    -0.65
     Pathways
    -0.64
    endsWith
    -0.63
    POSITIVE LOGITS
     crossing
    6.41
    crossing
    5.41
     crossed
    5.41
    Crossing
    5.22
     Crossing
    5.22
     crosses
    5.00
     crossings
    4.91
    crossed
    4.34
     cross
    4.22
    CROSS
    3.89
    Activations Density 0.113%

    No Known Activations