© 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. 57132
    Prev
    Next
    INDEX
    Explanations

    perspective and rotation transformations

    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
     night
    -0.89
    下降
    -0.81
     ночи
    -0.81
    azaki
    -0.73
    ractable
    -0.73
    ńcz
    -0.72
     χρη
    -0.69
     Night
    -0.69
    orca
    -0.68
     Better
    -0.68
    POSITIVE LOGITS
    perspective
    1.16
     perspective
    1.16
     rotations
    0.99
     Perspective
    0.94
     perspec
    0.93
     rotation
    0.93
    Perspective
    0.93
     PERSPECT
    0.93
     perspectives
    0.89
     ZTE
    0.89
    Activations Density 0.019%

    No Known Activations