© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119786
    Prev
    Next
    INDEX
    Explanations

    am pm time expressions

    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
     this
    -2.28
     these
    -1.75
     because
    -1.71
     -
    -1.52
     during
    -1.48
     with
    -1.45
     preventing
    -1.35
     besonders
    -1.34
     creating
    -1.34
     by
    -1.32
    POSITIVE LOGITS
    屣
    1.41
    毉
    1.41
    鸶
    1.41
     Jezus
    1.38
    䜣
    1.36
     unicórnio
    1.35
    臜
    1.35
     combustível
    1.35
     hout
    1.35
    湏
    1.34
    Activations Density 0.033%

    No Known Activations