© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62605
    Prev
    Next
    INDEX
    Explanations

    colors and clarity of water

    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
    Negative Logits
    checkable
    -0.90
    chauss
    -0.88
    nossa
    -0.88
     riverside
    -0.83
    مزید
    -0.83
    FIELD
    -0.82
    ῶν
    -0.81
    rought
    -0.81
    火
    -0.81
     Waterproof
    -0.79
    POSITIVE LOGITS
     blue
    1.63
     crystal
    1.62
     clear
    1.58
     emerald
    1.42
     turquoise
    1.39
     azure
    1.38
     azul
    1.35
     clearest
    1.21
    clear
    1.16
    blue
    1.16
    Activations Density 0.014%

    No Known Activations