© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45331
    Prev
    Next
    INDEX
    Explanations

    tul or thul sequences

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

    names or words that begin with "Tul" or contain "tule", possibly related to place names or proper nouns.

    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_34/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
     any
    -1.01
    either
    -0.77
     Zag
    -0.77
     totalt
    -0.75
    HX
    -0.75
    fiable
    -0.73
     either
    -0.73
     entstand
    -0.73
    Any
    -0.73
     можем
    -0.72
    POSITIVE LOGITS
    Tul
    0.91
    ancing
    0.81
     TUL
    0.80
     Tul
    0.80
     तुल
    0.77
    alaska
    0.75
    تول
    0.74
     Soledad
    0.73
     Tuli
    0.72
    ENCIES
    0.71
    Activations Density 0.012%

    No Known Activations