© 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. 33852
    Prev
    Next
    INDEX
    Explanations

    projection onto

    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
    ikations
    -0.79
    roke
    -0.68
     grapes
    -0.68
     IRQ
    -0.68
     тро
    -0.67
    Fiction
    -0.66
     tarifi
    -0.66
    getIn
    -0.66
     overheard
    -0.66
     mense
    -0.66
    POSITIVE LOGITS
     projection
    1.23
     onto
    1.23
     orthogonal
    1.12
     proj
    1.12
     projecting
    1.09
     projects
    1.07
    Proj
    0.91
     project
    0.90
     projections
    0.90
     Projection
    0.90
    Activations Density 0.025%

    No Known Activations