© 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. 10-GEMMASCOPE-RES-131K
    7. 61397
    Prev
    Next
    INDEX
    Explanations

    just + imperative verbs

    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_10/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
    ↵↵↵
    -1.99
    </h4>
    -1.66
     STILL
    -1.63
     این
    -1.52
    róleo
    -1.48
     värld
    -1.47
    </h3>
    -1.46
    ↵↵
    -1.45
    entitled
    -1.42
    illigen
    -1.41
    POSITIVE LOGITS
     that
    1.66
     them
    1.60
    目前的
    1.41
     ledit
    1.38
    begin
    1.36
     or
    1.34
    先前
    1.32
     your
    1.32
     without
    1.30
    再来
    1.30
    Activations Density 0.020%

    No Known Activations