© 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. 75344
    Prev
    Next
    INDEX
    Explanations

    Callum Field, local complications, unrecognized option

    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
    Surprisingly
    -3.09
     Ironically
    -2.95
     Surprisingly
    -2.88
     Interestingly
    -2.88
    Ironically
    -2.83
     unrelenting
    -2.80
     What
    -2.64
     Considering
    -2.59
    Several
    -2.53
            
    -2.52
    POSITIVE LOGITS
    ნ
    3.30
    艄
    3.14
    麁
    2.67
    ſſen
    2.58
     of
    2.41
    蠖
    2.34
    ︐
    2.30
    
    2.27
    喱
    2.25
    
    2.22
    Activations Density 0.000%

    No Known Activations