© 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. 109542
    Prev
    Next
    INDEX
    Explanations

    SQL queries with WHERE clauses

    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
     from
    -1.10
     creating
    -0.99
     any
    -0.90
     Creating
    -0.90
    groupId
    -0.88
    ు
    -0.86
     getting
    -0.86
     richting
    -0.85
    нь
    -0.84
    orkshire
    -0.84
    POSITIVE LOGITS
     where
    1.77
     WHERE
    1.55
    where
    1.16
    Où
    1.11
     где
    1.11
     donde
    1.04
     as
    1.02
     NATURAL
    0.99
    Where
    0.98
    表
    0.96
    Activations Density 0.044%

    No Known Activations