© 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. 22-GEMMASCOPE-RES-131K
    7. 95766
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    などが
    -1.81
    そして
    -1.71
     to
    -1.63
    があり
    -1.55
    などを
    -1.52
    与此同时
    -1.50
    Также
    -1.44
    目的是
    -1.42
    があります
    -1.41
    はなく
    -1.40
    POSITIVE LOGITS
    -
    1.91
    ほら
    1.62
    ええ
    1.57
    をします
    1.57
    ところに
    1.55
    ごめん
    1.52
    為に
    1.52
    すっ
    1.48
    '
    1.46
    に挑戦
    1.44
    Activations Density 0.001%

    No Known Activations