© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49387
    Prev
    Next
    INDEX
    Explanations

    ipsilateral

    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
     Slow
    -0.81
    liste
    -0.78
     Ame
    -0.72
    Slow
    -0.71
     Karp
    -0.71
    export
    -0.69
    ͇
    -0.68
    slow
    -0.67
     Orange
    -0.67
     much
    -0.65
    POSITIVE LOGITS
     IP
    1.22
     Ip
    1.06
     Ips
    1.05
    IP
    1.00
     ips
    0.97
     IPT
    0.92
     ip
    0.92
    Ip
    0.90
     IPS
    0.88
    IPO
    0.87
    Activations Density 0.031%

    No Known Activations