© 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. 65537
    Prev
    Next
    INDEX
    Explanations

    circadian rhythm, ambient meditation

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

    references to specialized technical terms, organizations, or systems (like "circadian rhythm", "injunctive norms", "F.C.", "CalTrans").

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     into
    -1.80
     is
    -1.56
    ilty
    -1.54
     was
    -1.47
     should
    -1.45
     měla
    -1.44
    Niveau
    -1.44
     can
    -1.42
    Теперь
    -1.39
    ーズン
    -1.34
    POSITIVE LOGITS
    ocidade
    1.69
     diferentes
    1.59
     yesterday
    1.58
     también
    1.52
     otros
    1.47
     yester
    1.45
     otras
    1.43
     vč
    1.43
     last
    1.42
     empez
    1.42
    Activations Density 0.185%

    No Known Activations