© 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. 22-GEMMASCOPE-RES-131K
    7. 93001
    Prev
    Next
    INDEX
    Explanations

    growth and transformation

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

    narratives about something small transforming into something significant or unexpected.

    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_22/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
    nologies
    -1.00
     особенно
    -0.94
     andato
    -0.94
     estekak
    -0.93
     TÜ
    -0.88
    ያ
    -0.88
    estres
    -0.88
    więcej
    -0.87
    뢰
    -0.87
     particularly
    -0.85
    POSITIVE LOGITS
     become
    1.13
     turned
    1.13
     transformed
    1.08
     became
    1.05
    turned
    1.02
    transformed
    0.95
     оказался
    0.91
     تبدیل
    0.89
    become
    0.89
     ended
    0.89
    Activations Density 0.075%

    No Known Activations