© 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. 54041
    Prev
    Next
    INDEX
    Explanations

    rotate and view 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
    wealth
    -0.72
    觅
    -0.71
    Qd
    -0.69
     još
    -0.69
    😷
    -0.68
    underwater
    -0.68
     Giappone
    -0.68
     얼
    -0.68
    Laws
    -0.68
    tactos
    -0.68
    POSITIVE LOGITS
     viewpoint
    1.04
     rotations
    1.00
     viewing
    0.96
     elev
    0.95
    elev
    0.92
     projection
    0.91
     rotate
    0.87
     POV
    0.84
     wire
    0.84
     view
    0.84
    Activations Density 0.009%

    No Known Activations