© 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. 104757
    Prev
    Next
    INDEX
    Explanations

    "arbor", "arbo", "Arborophila", "Arboleda", "arbovirus", "albero"

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

    names that have a specific pattern, especially surnames like "Arboleda", "Nussimbaum", "arbor", and phrases like "Tree of Life".

    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
    ↵
    -2.17
    跸
    -2.08
    硨
    -2.02
     faisant
    -1.99
    ⟣
    -1.95
     toujours
    -1.92
    坶
    -1.92
    ︐
    -1.91
    ぶつ
    -1.88
     inextrica
    -1.88
    POSITIVE LOGITS
    𓆜
    2.69
     vulgares
    2.27
    </h3>
    2.27
    this
    2.16
    "));
    2.14
    杪
    2.06
    AT
    2.00
    </u>
    2.00
     універ
    2.00
     silencioso
    1.98
    Activations Density 0.005%

    No Known Activations