© 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. 10-GEMMASCOPE-RES-131K
    7. 75349
    Prev
    Next
    INDEX
    Explanations

    trapezoidal shapes and rules

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of the word “trapezoid” (in any morphological or compound form)

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     But
    -2.38
                
    -2.30
    );
    -2.27
    9
    -2.23
          
    -2.20
                    
    -2.20
    in
    -2.11
    H
    -2.06
    1
    -2.06
    攆
    -2.02
    POSITIVE LOGITS
    婠
    2.20
     tomadas
    2.06
    ⋈
    2.02
     pedimos
    1.99
    沨
    1.89
     salarios
    1.85
     ponemos
    1.84
     fantástica
    1.84
     hicimos
    1.82
     damos
    1.81
    Activations Density 0.005%

    No Known Activations