© 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. 10-GEMMASCOPE-RES-131K
    4. 69005
    Prev
    Next
    INDEX
    Explanations

    preparing for events or tasks

    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_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
    their
    -1.55
     réalisateur
    -1.53
     vai
    -1.52
     erneu
    -1.46
    わけではない
    -1.43
    那就是
    -1.43
    𝐇
    -1.43
    EDING
    -1.41
    ヒル
    -1.40
    嫉妒
    -1.40
    POSITIVE LOGITS
     This
    1.84
    vanju
    1.63
     Perhaps
    1.55
     Shortly
    1.49
     and
    1.49
     Often
    1.49
     könnten
    1.48
     Usually
    1.46
     Certainly
    1.45
     riservata
    1.44
    Activations Density 0.026%

    No Known Activations