© 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. 86755
    Prev
    Next
    INDEX
    Explanations

    questions starting with what or Q

    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
    nadequate
    -1.82
    atized
    -1.73
     москве
    -1.72
    dienne
    -1.70
    Mvh
    -1.66
    vermectin
    -1.66
     dekol
    -1.66
    ༛
    -1.65
    谎
    -1.63
    ୌ
    -1.63
    POSITIVE LOGITS
     to
    2.98
     from
    2.70
     by
    2.66
     with
    2.64
     and
    2.52
     on
    2.14
     is
    2.14
     in
    2.02
     at
    2.00
     like
    1.98
    Activations Density 0.001%

    No Known Activations