© 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. 11994
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and links

    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
     any
    -1.63
    ↵↵
    -1.52
     pediu
    -1.51
     decidiu
    -1.48
     estadual
    -1.42
     I
    -1.41
     seule
    -1.40
     only
    -1.39
     saiu
    -1.38
    1
    -1.38
    POSITIVE LOGITS
     terciopelo
    1.59
    峮
    1.51
     FEBRUARY
    1.44
    )$.
    1.38
     septem
    1.38
     饼
    1.37
     ہیں۔
    1.37
     图案
    1.37
    ㄩ
    1.35
    |'\
    1.34
    Activations Density 0.007%

    No Known Activations