© 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. 34-GEMMASCOPE-RES-131K
    7. 50205
    Prev
    Next
    INDEX
    Explanations

    holes, gaps, and flaws

    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
     tré
    -0.73
    ಷ್
    -0.69
     maat
    -0.68
     лента
    -0.67
    ㅉ
    -0.67
     näher
    -0.66
     تجمعات
    -0.66
    vering
    -0.64
     lì
    -0.63
    chok
    -0.63
    POSITIVE LOGITS
     holes
    5.78
     hole
    4.59
     Holes
    4.38
    holes
    4.31
     gaps
    4.31
    Holes
    3.91
    hole
    3.73
    Hole
    3.72
     Hole
    3.58
     HOLE
    3.38
    Activations Density 0.102%

    No Known Activations