© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68229
    Prev
    Next
    INDEX
    Explanations

    specific niche terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    為に
    -1.69
    の方に
    -1.66
    際には
    -1.52
    の方も
    -1.52
    の準備
    -1.50
    ところに
    -1.44
    の詳細
    -1.44
    ことも
    -1.41
    気がします
    -1.40
    来週
    -1.38
    POSITIVE LOGITS
    があり
    1.73
    を
    1.68
    がありますが
    1.59
    <bos>
    1.48
    がある
    1.48
    妖精
    1.41
    があります
    1.40
    などを
    1.38
    そして
    1.36
    が
    1.34
    Activations Density 0.121%

    No Known Activations