© 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. 104683
    Prev
    Next
    INDEX
    Explanations

    outcomes and results

    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
     its
    -2.38
     it
    -1.89
     with
    -1.50
     there
    -1.38
     two
    -1.38
    its
    -1.31
     if
    -1.27
     has
    -1.19
     one
    -1.17
     from
    -1.16
    POSITIVE LOGITS
    他们的
    1.50
     jejich
    1.45
    rogels
    1.35
    ació
    1.31
    toThrow
    1.29
    ClientSize
    1.26
     deviennent
    1.23
    lichkeit
    1.22
     ofta
    1.22
     Их
    1.21
    Activations Density 0.124%

    No Known Activations