© 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. 34-GEMMASCOPE-RES-131K
    7. 64982
    Prev
    Next
    INDEX
    Explanations

    URL and permalinks

    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
    Hunting
    -0.79
     hunting
    -0.75
    hunting
    -0.69
     FJ
    -0.68
     Patria
    -0.68
    Beschreibung
    -0.67
    샐
    -0.66
    alarme
    -0.65
     Spreadsheet
    -0.65
     Га
    -0.65
    POSITIVE LOGITS
     URL
    2.58
     url
    2.58
    url
    2.31
    URL
    2.30
     URLs
    2.20
    Url
    2.13
    getUrl
    1.94
     URI
    1.91
     Url
    1.79
    uri
    1.73
    Activations Density 0.190%

    No Known Activations