© 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. 78663
    Prev
    Next
    INDEX
    Explanations

    lightness and color descriptions

    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
    ♝
    -0.79
    🦰
    -0.74
     черные
    -0.74
    enio
    -0.73
    ToLeft
    -0.72
    edakan
    -0.72
     alumno
    -0.72
    ラマ
    -0.70
    Stderr
    -0.70
     dicendo
    -0.70
    POSITIVE LOGITS
     lighter
    3.53
     lighten
    2.97
     light
    2.77
     lightening
    2.70
     lightest
    2.59
     Lighter
    2.59
    lighter
    2.58
     свет
    2.55
     bright
    2.44
     Light
    2.36
    Activations Density 0.047%

    No Known Activations