© 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. 11836
    Prev
    Next
    INDEX
    Explanations

    punctuation and separators

    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
     長袖
    -1.59
    PARATION
    -1.53
     naïve
    -1.51
    、
    -1.49
    Ⅴ
    -1.48
    可以
    -1.45
     após
    -1.43
    끽
    -1.42
     

    -1.37
            
    -1.36
    POSITIVE LOGITS
     Of
    1.53
     at
    1.46
     eşofman
    1.42
     A
    1.33
    1
    1.32
    =\
    1.29
     của
    1.29
    j
    1.26
     sposób
    1.25
    跸
    1.25
    Activations Density 0.079%

    No Known Activations