© 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. 105012
    Prev
    Next
    INDEX
    Explanations

    being suspended

    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
     astounding
    -3.05
     astonishing
    -2.97
     startling
    -2.78
     gruesome
    -2.69
     amazing
    -2.69
     ferocious
    -2.66
     sorrow
    -2.66
     incredibly
    -2.63
     dismal
    -2.59
     моей
    -2.52
    POSITIVE LOGITS
    ↵
    3.84
    酲
    2.69
    沇
    2.53
     grijs
    2.52
    趼
    2.48
    ांकि
    2.44
    鄠
    2.41
    ⽌
    2.39
    轫
    2.33
     terwijl
    2.31
    Activations Density 0.006%

    No Known Activations