© 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. 65583
    Prev
    Next
    INDEX
    Explanations

    aspect ratio

    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
     lukewarm
    -0.85
    월
    -0.81
    Ок
    -0.79
    wann
    -0.75
    voiced
    -0.74
     temperaturas
    -0.73
    פש
    -0.73
    ₂+
    -0.72
    zeppelin
    -0.72
     שיש
    -0.72
    POSITIVE LOGITS
     ratio
    2.58
     aspect
    2.41
     ratios
    2.31
    ratio
    2.11
    Ratio
    2.06
     Ratio
    1.97
     Ratios
    1.87
    RATIO
    1.84
    AspectRatio
    1.84
    aspect
    1.81
    Activations Density 0.026%

    No Known Activations