© 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. 66430
    Prev
    Next
    INDEX
    Explanations

    questions, titles, or code blocks

    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
     koron
    -1.59
     STATE
    -1.48
     kamera
    -1.48
     paru
    -1.47
    schen
    -1.46
     kommunik
    -1.45
     klas
    -1.43
    ᕮ
    -1.43
     amerikan
    -1.41
     wła
    -1.41
    POSITIVE LOGITS
    様な
    1.36
    来週
    1.32
    ↵↵
    1.23
    為に
    1.23
    つづく
    1.22
    ツイッター
    1.20
     vervolgens
    1.20
     zwięks
    1.17
     będę
    1.17
    可能會
    1.15
    Activations Density 0.000%

    No Known Activations