© 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. 100825
    Prev
    Next
    INDEX
    Explanations

    only, Q, Lip lipids

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

    phrases indicating a continuation or condition, often after words like "only," "when," "if," or at the end of a sentence.

    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
     bordado
    -2.06
    ᜀ
    -1.95
     verhind
    -1.91
     bâton
    -1.87
    ,"
    -1.87
     بازار
    -1.79
    ンプー
    -1.77
     kompatibel
    -1.77
     risiko
    -1.76
     estampado
    -1.75
    POSITIVE LOGITS
     and
    1.96
    wa
    1.76
    man
    1.67
     când
    1.66
    但
    1.55
     focussing
    1.52
     to
    1.51
    uk
    1.50
    up
    1.49
     diversos
    1.48
    Activations Density 0.000%

    No Known Activations