© 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. 106959
    Prev
    Next
    INDEX
    Explanations

    glass, window, cover, lenses

    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
     Occidente
    -0.77
    lucent
    -0.77
    chieht
    -0.74
    راعة
    -0.70
     oeste
    -0.69
     pós
    -0.69
    之助
    -0.68
    壁紙
    -0.67
    pédie
    -0.67
     письмен
    -0.67
    POSITIVE LOGITS
     glass
    1.74
    玻璃
    1.27
    glass
    1.18
    ガラス
    1.13
     Glass
    1.06
    Glass
    1.05
     cover
    0.94
    強化
    0.91
     GLASS
    0.91
     plex
    0.88
    Activations Density 0.031%

    No Known Activations