© 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. 65549
    Prev
    Next
    INDEX
    Explanations

    in or for or by

    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
     probably
    -2.00
     distinctly
    -1.94
     multifaceted
    -1.88
     supremely
    -1.87
     mildly
    -1.86
     what
    -1.80
     meticulous
    -1.80
     markedly
    -1.75
     undoubtedly
    -1.74
     interestingly
    -1.73
    POSITIVE LOGITS
    s
    1.85
     usando
    1.75
     diversos
    1.72
     acclaimed
    1.70
     dando
    1.62
    despite
    1.59
     oa
    1.53
    tt
    1.48
    ры
    1.46
    various
    1.45
    Activations Density 0.022%

    No Known Activations