© 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. 61052
    Prev
    Next
    INDEX
    Explanations

    initiating phrases and questions

    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
    ,
    -1.57
     is
    -1.55
     laikā
    -1.52
    bsc
    -1.46
     --
    -1.45
               
    -1.43
          
    -1.41
     erneut
    -1.40
    harf
    -1.39
     “
    -1.37
    POSITIVE LOGITS
    </tr>
    1.82
    蒹
    1.79
     plafon
    1.66
    Namun
    1.66
    ❢
    1.62
    }}\
    1.59
    Tetapi
    1.56
    Bahkan
    1.53
    ofing
    1.53
     gratuite
    1.53
    Activations Density 0.007%

    No Known Activations