© 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. 68707
    Prev
    Next
    INDEX
    Explanations

    object deletion

    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
    generally
    -1.03
     ensimmä
    -1.00
    rigs
    -1.00
     desenhos
    -1.00
    petition
    -0.97
    aneity
    -0.96
    spreis
    -0.96
    uus
    -0.95
    ">“
    -0.94
    ViewFeatures
    -0.94
    POSITIVE LOGITS
    würdig
    1.06
     portare
    0.98
    hängig
    0.90
     reputable
    0.90
    ファイルを
    0.89
     brought
    0.86
    Fastest
    0.85
     dieses
    0.85
    Stap
    0.85
     from
    0.85
    Activations Density 0.002%

    No Known Activations