© 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. 69322
    Prev
    Next
    INDEX
    Explanations

    fanfic, fic, art, zine, mixtape

    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
    }
    -1.87
    もお
    -1.84
     but
    -1.79
    –
    -1.77
     It
    -1.71
     mindful
    -1.68
               
    -1.62
    â
    -1.61
     semua
    -1.59
    "
    -1.59
    POSITIVE LOGITS
    
    2.39
    ፒ
    2.03
    ﹶ
    2.02
    .”
    1.95
     diki
    1.93
     sabun
    1.93
    ጳ
    1.88
     概要
    1.88
     huden
    1.85
     kapak
    1.79
    Activations Density 0.004%

    No Known Activations