© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112958
    Prev
    Next
    INDEX
    Explanations

    units with following punctuation

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

    units of measurement abbreviations, particularly those indicating rates or frequencies (like "cpm", "ppi", "kph", "mph", "Mbps", "kps").

    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
     to
    -2.55
    </th>
    -1.87
     {
    -1.85
    なども
    -1.80
    を作る
    -1.80
     up
    -1.75
    ommation
    -1.74
    们的
    -1.70
    %;
    -1.70
    へ行
    -1.67
    POSITIVE LOGITS
    ?"
    2.05
     ceket
    1.91
    This
    1.88
    。"
    1.84
    8
    1.79
    7
    1.74
     作り方
    1.70
    ！”
    1.63
    ！"
    1.62
    。　　
    1.59
    Activations Density 0.020%

    No Known Activations