© 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. 12723
    Prev
    Next
    INDEX
    Explanations

    numbers or symbols followed by punctuation

    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
     because
    -1.73
    </sup>
    -1.66
     they
    -1.51
     when
    -1.50
     then
    -1.46
     if
    -1.43
    他们
    -1.40
     rendono
    -1.34
     strass
    -1.34
    š
    -1.33
    POSITIVE LOGITS
     —
    2.13
     
    1.73
    >
    1.56
    返す
    1.42
    对待
    1.38
     "
    1.36
    異なります
    1.34
    くらいの
    1.33
    前辈
    1.33
     mesmos
    1.32
    Activations Density 0.049%

    No Known Activations