© 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. 49268
    Prev
    Next
    INDEX
    Explanations

    directional light

    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
    ALICE
    -0.75
    ühne
    -0.75
    hdessä
    -0.73
     endpoints
    -0.70
    Raf
    -0.70
    Hui
    -0.69
     Transparent
    -0.69
    ᚾ
    -0.68
    ͺ
    -0.68
     GEM
    -0.67
    POSITIVE LOGITS
     light
    1.44
     lights
    1.36
     directional
    1.34
     direction
    1.26
     lamp
    1.25
    directional
    1.24
     Light
    1.18
     LIGHT
    1.15
    Directional
    1.14
     sources
    1.13
    Activations Density 0.010%

    No Known Activations