© 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. 111924
    Prev
    Next
    INDEX
    Explanations

    will followed by a verb

    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
     الأخرى
    -1.51
    IndentedString
    -1.45
    Poznám
    -1.43
    が
    -1.38
     altres
    -1.38
    Therefore
    -1.37
    haikusbot
    -1.35
    vosti
    -1.34
     anderen
    -1.33
    Примеча
    -1.33
    POSITIVE LOGITS
     to
    1.38
     llegan
    1.32
     letzt
    1.21
     applicable
    1.20
     plentiful
    1.16
     amizade
    1.14
     such
    1.13
     wichtigsten
    1.13
    感じる
    1.12
     constituyen
    1.12
    Activations Density 0.026%

    No Known Activations