© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109807
    Prev
    Next
    INDEX
    Explanations

    SQL rows. statements. expression

    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
    pumpkin
    -0.82
    🔸
    -0.77
     محافظة
    -0.74
    collana
    -0.74
    MongoDB
    -0.74
    rotating
    -0.73
     beschik
    -0.73
     egenskaper
    -0.72
     prochaines
    -0.69
    Albany
    -0.69
    POSITIVE LOGITS
     rows
    1.04
     SQL
    1.01
     sql
    0.92
    pg
    0.91
    returning
    0.89
    expression
    0.88
     ROW
    0.86
    stmt
    0.85
     expression
    0.85
    CompilerServices
    0.84
    Activations Density 0.011%

    No Known Activations