© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63463
    Prev
    Next
    INDEX
    Explanations

    Maya and MEL scripting

    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
     splicing
    -0.74
    viating
    -0.73
     conformance
    -0.72
    ANTAGES
    -0.70
    autop
    -0.69
     malic
    -0.69
    Brat
    -0.69
     doze
    -0.69
     breech
    -0.69
     encara
    -0.68
    POSITIVE LOGITS
    PostInfinity
    0.99
     MEL
    0.93
     Connections
    0.91
     Maya
    0.89
    Attr
    0.88
     maya
    0.87
     shelf
    0.85
     shelves
    0.82
    connections
    0.82
    mel
    0.81
    Activations Density 0.018%

    No Known Activations