© 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. 118741
    Prev
    Next
    INDEX
    Explanations

    questions and agreements

    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
    ↵
    -2.00
    骉
    -1.80
     🥰
    -1.40
    rrrrr
    -1.40
     zen
    -1.39
    ‘
    -1.36
     feme
    -1.33
     expanse
    -1.32
    kkk
    -1.32
     there
    -1.30
    POSITIVE LOGITS
     those
    1.80
     new
    1.66
    σεις
    1.64
     estos
    1.59
    ного
    1.56
     declaraciones
    1.56
     appalled
    1.55
     longtime
    1.55
     citoy
    1.54
     whats
    1.51
    Activations Density 0.005%

    No Known Activations