© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119100
    Prev
    Next
    INDEX
    Explanations

    return false

    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_34/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
    Né
    -0.94
     rozmiar
    -0.91
    Cé
    -0.82
     publicó
    -0.79
    Én
    -0.77
    クト
    -0.77
    লা
    -0.77
     Unmarshal
    -0.76
    ަ
    -0.76
     Né
    -0.74
    POSITIVE LOGITS
     false
    2.00
     return
    1.74
     returning
    1.57
    return
    1.50
    false
    1.40
     Returning
    1.37
     False
    1.34
     Return
    1.31
     FALSE
    1.28
    Returning
    1.24
    Activations Density 0.017%

    No Known Activations