© 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. 10-GEMMASCOPE-RES-131K
    7. 127480
    Prev
    Next
    INDEX
    Explanations

    name initials

    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_10/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
     to
    -2.13
     téc
    -1.61
     as
    -1.55
    着一个
    -1.55
    着一
    -1.55
     itself
    -1.49
     szkole
    -1.46
     sentimenti
    -1.45
     också
    -1.45
    ന്റെ
    -1.43
    POSITIVE LOGITS
     you
    1.56
    quartered
    1.50
    .
    1.46
    taglio
    1.45
    WARDS
    1.45
    urized
    1.40
    olesterol
    1.39
     ekor
    1.34
    ________________
    1.33
    grained
    1.33
    Activations Density 0.020%

    No Known Activations