Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8066
    Prev
    Next
    INDEX
    Explanations

    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
    riceps
    -1.07
    下に
    -0.83
    дже
    -0.81
    לות
    -0.80
    Vee
    -0.78
    Ours
    -0.78
    יני
    -0.78
    brie
    -0.77
    Yh
    -0.77
    beheer
    -0.74
    POSITIVE LOGITS
     where
    3.84
     WHERE
    3.30
    Where
    3.25
     Where
    3.16
    WHERE
    3.13
    where
    3.11
     conditions
    2.30
     condition
    2.19
    condition
    2.00
    wheres
    1.95
    Activations Density 0.079%

    No Known Activations