© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103011
    Prev
    Next
    INDEX
    Explanations

    abstracts and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers embedded within technical or code contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     which
    -2.05
    呖
    -1.59
    焄
    -1.54
     kuris
    -1.52
     whose
    -1.50
     rígido
    -1.49
     íntimo
    -1.47
     delicado
    -1.45
     your
    -1.44
     οποίο
    -1.41
    POSITIVE LOGITS
    Somehow
    1.40
     irres
    1.36
     indef
    1.34
     inim
    1.32
    cisive
    1.31
     quelle
    1.30
    Either
    1.27
     choc
    1.25
     '
    1.23
    olkata
    1.23
    Activations Density 0.305%

    No Known Activations