© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 568
    Prev
    Next
    INDEX
    Explanations

    protective headwear and eyewear

    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
    ing
    -1.48
    魨
    -1.36
     SPAIN
    -1.34
    mpagne
    -1.34
     einde
    -1.25
     CHLOR
    -1.23
    Estonia
    -1.22
    嫫
    -1.20
     Dokumentation
    -1.18
    뮐
    -1.18
    POSITIVE LOGITS
    Already
    1.44
    You
    1.36
    If
    1.34
    Not
    1.34
    ITY
    1.29
    Always
    1.25
    After
    1.23
     use
    1.23
     giras
    1.22
    The
    1.21
    Activations Density 0.031%

    No Known Activations