© 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. 22-GEMMASCOPE-RES-131K
    7. 72802
    Prev
    Next
    INDEX
    Explanations

    package names and compound words

    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_22/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
     asfalto
    -1.67
    และ
    -1.67
     silikon
    -1.57
     pañ
    -1.56
     cinto
    -1.55
     casco
    -1.55
     kolon
    -1.55
     calça
    -1.54
    
    -1.53
     pelu
    -1.52
    POSITIVE LOGITS
    It
    1.89
    is
    1.82
    _
    1.73
    u
    1.73
    O
    1.66
    D
    1.65
    f
    1.63
    B
    1.62
    L
    1.62
    A
    1.61
    Activations Density 0.013%

    No Known Activations