© 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. 130727
    Prev
    Next
    INDEX
    Explanations

    oncology and morse code punctuation

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

    punctuation marks followed by dashes, particularly in headers or datelines like "Calif.--" or ".--".

    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
     We
    -2.77
    鲩
    -2.66
    /
    -2.64
     или
    -2.61
     один
    -2.34
    หรือ
    -2.33
    躄
    -2.31
    ⎔
    -2.27
     เรา
    -2.27
    ).
    -2.27
    POSITIVE LOGITS
    t
    2.98
    銦
    2.91
    er
    2.83
    ing
    2.72
    ة
    2.52
    ed
    2.50
     utilizzati
    2.50
    ta
    2.44
    ar
    2.44
    .—
    2.39
    Activations Density 0.002%

    No Known Activations