© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13419
    Prev
    Next
    INDEX
    Explanations

    any character

    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
    Manfaat
    -1.28
    Daha
    -1.20
    você
    -1.20
     žena
    -1.19
     jums
    -1.18
    çok
    -1.18
    käse
    -1.16
    Çok
    -1.16
    võ
    -1.16
    kadın
    -1.13
    POSITIVE LOGITS
     to
    1.15
     any
    1.15
     other
    1.02
     or
    0.89
     cualquier
    0.88
     любой
    0.87
     zufolge
    0.87
     &
    0.85
     did
    0.85
    菁
    0.85
    Activations Density 0.000%

    No Known Activations