© 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. 10073
    Prev
    Next
    INDEX
    Explanations

    Anno, Attn, insignificantly, Embarrassing, amino, Brenner

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

    Latin-derived terms and abbreviations like "Anno", "Attn", "insignus", and "amino".

    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
     houſe
    -2.89
    辚
    -2.78
    一个是
    -2.78
    gucig
    -2.67
    戩
    -2.58
     kraju
    -2.56
    écoute
    -2.55
     умова
    -2.55
     แต่
    -2.52
    髏
    -2.52
    POSITIVE LOGITS
    en
    3.78
    .
    3.48
    O
    3.22
    u
    3.13
     =
    3.05
    it
    2.84
    a
    2.81
    ↵
    2.75
    <em>
    2.61
    <b>
    2.59
    Activations Density 0.003%

    No Known Activations