© 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. 83073
    Prev
    Next
    INDEX
    Explanations

    sql `WHERE` clauses and logical operators

    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
     that
    -1.13
     while
    -1.02
     where
    -0.95
     metodo
    -0.93
     how
    -0.88
     artesanato
    -0.86
    >.</
    -0.85
    ,
    -0.84
     teolog
    -0.84
     romantis
    -0.83
    POSITIVE LOGITS
     and
    2.69
     AND
    1.85
     и
    1.45
     And
    1.42
    AND
    1.38
     και
    1.30
     và
    1.26
     และ
    1.24
     or
    1.22
     OR
    1.20
    Activations Density 0.018%

    No Known Activations