© 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. 15209
    Prev
    Next
    INDEX
    Explanations

    data field identifiers

    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
     praktis
    -1.95
     berge
    -1.94
     recensement
    -1.86
     siè
    -1.84
     koste
    -1.77
     kalender
    -1.73
     kosme
    -1.71
     parfü
    -1.68
    announced
    -1.67
     territoriale
    -1.66
    POSITIVE LOGITS
     date
    1.90
     location
    1.88
     time
    1.84
     type
    1.79
     total
    1.64
     description
    1.63
     T
    1.63
     L
    1.58
     details
    1.58
     was
    1.55
    Activations Density 0.014%

    No Known Activations