© 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. 30382
    Prev
    Next
    INDEX
    Explanations

    words starting with poly

    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
    فاق
    -0.87
     spare
    -0.81
     McCle
    -0.77
     gently
    -0.77
    Make
    -0.76
     comprometido
    -0.76
    ủng
    -0.74
     relating
    -0.74
     læng
    -0.73
    われます
    -0.72
    POSITIVE LOGITS
    ＂
    0.89
    POLY
    0.89
     POLY
    0.86
     sodio
    0.86
     gånger
    0.82
    
    0.81
    ону
    0.77
    nais
    0.77
    ンズ
    0.77
    byen
    0.77
    Activations Density 0.061%

    No Known Activations