© 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. 104130
    Prev
    Next
    INDEX
    Explanations

    AWS arn

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

    the text sequence "arn" appearing within words or names.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    呖
    -3.84
    鋮
    -3.42
    🩻
    -3.25
    躝
    -3.17
    蹀
    -3.03
    ቷ
    -2.97
     всѣ
    -2.78
    踅
    -2.69
    錵
    -2.67
    攆
    -2.64
    POSITIVE LOGITS
    I
    3.34
    S
    3.09
    O
    3.02
    M
    2.83
     Your
    2.73
    arn
    2.67
    E
    2.66
    K
    2.66
     These
    2.64
    P
    2.56
    Activations Density 0.001%

    No Known Activations