© 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. 65021
    Prev
    Next
    INDEX
    Explanations

    web requests and code delimiters

    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
     wich
    -1.51
     (‘
    -1.45
     ‘
    -1.44
    -1.37
    which
    -1.37
     then
    -1.35
    PARATION
    -1.32
     Which
    -1.30
     recounts
    -1.26
    ffi
    -1.26
    POSITIVE LOGITS
     accompagner
    1.56
    たまた
    1.56
    泚
    1.52
    iyle
    1.45
     to
    1.38
     keinerlei
    1.30
     ausschließlich
    1.29
    ANIEL
    1.29
    owohl
    1.28
     avancer
    1.28
    Activations Density 0.009%

    No Known Activations