© 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. 39153
    Prev
    Next
    INDEX
    Explanations

    code declarations

    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
    r
    -1.60
    大致
    -1.46
    sthe
    -1.45
    Dalam
    -1.39
    t
    -1.38
    znego
    -1.38
    n
    -1.36
    太大
    -1.35
    poner
    -1.32
     impor
    -1.30
    POSITIVE LOGITS
    .
    1.84
     way
    1.63
     only
    1.59
     like
    1.52
     in
    1.52
    ."
    1.52
     by
    1.46
     so
    1.46
    :
    1.45
     using
    1.41
    Activations Density 0.440%

    No Known Activations