© 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. 42320
    Prev
    Next
    INDEX
    Explanations

    what i need is

    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
     nawet
    -2.19
     vårt
    -1.72
     oorsp
    -1.70
     ➢
    -1.64
     onderdelen
    -1.64
     it
    -1.63
    还不错
    -1.57
     tegens
    -1.57
     verkoop
    -1.57
    低于
    -1.57
    POSITIVE LOGITS
     a
    3.75
     an
    2.14
     some
    1.97
     ließen
    1.70
     data
    1.55
    сите
    1.55
     something
    1.50
    тата
    1.49
     one
    1.45
    </strong>
    1.45
    Activations Density 0.026%

    No Known Activations