© 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. 78659
    Prev
    Next
    INDEX
    Explanations

    scores in sets

    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
    　　
    -0.81
     ocze
    -0.74
                       
    -0.73
                      
    -0.73
     الأربع
    -0.72
     Ethiopia
    -0.71
    คุ
    -0.71
    insured
    -0.70
     egiten
    -0.68
    隆
    -0.68
    POSITIVE LOGITS
     super
    0.94
    FABRIC
    0.86
    kozó
    0.82
     deciding
    0.81
     maak
    0.79
    Soils
    0.77
     tie
    0.77
    Cancell
    0.76
     kram
    0.76
    惰
    0.75
    Activations Density 0.014%

    No Known Activations