© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38952
    Prev
    Next
    INDEX
    Explanations

    lodging and availability

    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
    ╽
    -2.83
    ╿
    -2.72
    
    -2.64
    
    -2.59
     gjerne
    -2.53
    mpagne
    -2.47
     partecipa
    -2.45
    ⡯
    -2.38
    俛
    -2.34
     vostre
    -2.31
    POSITIVE LOGITS
     “
    2.86
    ↵
    2.86
    ,”
    2.77
    ?
    2.67
    (“
    2.67
    .
    2.50
    ICK
    2.48
    {
    2.44
    ating
    2.33
    賅
    2.27
    Activations Density 0.007%

    No Known Activations