© 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. 1031
    Prev
    Next
    INDEX
    Explanations

    information, news, and their falsehoods

    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
    ников
    -1.18
    ciuta
    -1.16
     misterioso
    -1.14
     kling
    -1.12
    кий
    -1.12
    此外
    -1.11
     dacă
    -1.10
     subwoofer
    -1.10
     jsonObject
    -1.09
     jeśli
    -1.09
    POSITIVE LOGITS
     about
    1.86
     information
    1.45
    它們
    1.35
    の情報
    1.32
     info
    1.24
    ężczy
    1.23
    information
    1.20
     such
    1.18
    の影響
    1.18
     informasi
    1.15
    Activations Density 0.093%

    No Known Activations