© 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. 19820
    Prev
    Next
    INDEX
    Explanations

    company names ending in Inc

    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
    
    -1.97
    Also
    -1.72
    The
    -1.70
    7
    -1.70
     leichten
    -1.65
    n
    -1.64
     troublesome
    -1.63
     According
    -1.62
    無論
    -1.62
     multitude
    -1.61
    POSITIVE LOGITS
    },
    2.33
     actriz
    1.81
     hvis
    1.80
     chè
    1.77
     flink
    1.76
    鉝
    1.75
     Dokter
    1.74
    釭
    1.74
    ==",
    1.73
     blau
    1.73
    Activations Density 0.045%

    No Known Activations