© 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. 10-GEMMASCOPE-RES-131K
    7. 12043
    Prev
    Next
    INDEX
    Explanations

    following specific words

    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
     tomto
    -1.69
     to
    -1.48
     nontrivial
    -1.40
     začet
    -1.33
    を使用した
    -1.32
     sinful
    -1.31
     comenz
    -1.29
     lors
    -1.29
     evento
    -1.27
     herhangi
    -1.27
    POSITIVE LOGITS
    estrado
    1.53
    化
    1.41
    因為
    1.41
    omiast
    1.41
     marino
    1.40
    żeń
    1.38
     marat
    1.32
    可以
    1.32
     conquête
    1.32
    All
    1.31
    Activations Density 0.122%

    No Known Activations