© 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. 13173
    Prev
    Next
    INDEX
    Explanations

    fast development and growth

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

    the word "fast" when used as an adjective in hyphenated phrases like "fast-growing" or "fast-paced".

    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
    8
    -1.98
    4
    -1.94
    5
    -1.94
    3
    -1.73
     la
    -1.61
     unlike
    -1.58
     ۳۰
    -1.53
     somewhat
    -1.53
     tremendous
    -1.51
     ۲۵
    -1.51
    POSITIVE LOGITS
     rých
    1.84
     新款
    1.81
     nejlepší
    1.66
    嗵
    1.63
    bagian
    1.63
     uygulama
    1.61
    📐
    1.60
     täh
    1.59
     ľah
    1.59
     rychle
    1.59
    Activations Density 0.021%

    No Known Activations