© 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. 34-GEMMASCOPE-RES-131K
    4. 25691
    Prev
    Next
    INDEX
    Explanations

    tamper-evident seals

    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_34/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
     getResources
    -0.75
    と思っています
    -0.75
     bảng
    -0.71
    פשר
    -0.71
    郞
    -0.71
    ߒ
    -0.71
    жаться
    -0.69
     Inbox
    -0.69
     fahr
    -0.68
    FUNCTION
    -0.68
    POSITIVE LOGITS
     seals
    3.23
     seal
    3.22
     sealed
    2.66
    seal
    2.53
     sealing
    2.48
    Seal
    2.38
    sealed
    2.36
     Seal
    2.31
     Seals
    2.27
    SEAL
    2.14
    Activations Density 0.019%

    No Known Activations