© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70951
    Prev
    Next
    INDEX
    Explanations

    announcements and titles

    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_22/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
     when
    -1.84
     it
    -1.84
     did
    -1.79
     after
    -1.73
     that
    -1.73
     talked
    -1.59
     only
    -1.56
     even
    -1.50
     their
    -1.47
     went
    -1.46
    POSITIVE LOGITS
    upto
    1.29
     aston
    1.28
    鐽
    1.27
     lesquels
    1.27
    ől
    1.23
     auparavant
    1.23
    脑海
    1.20
     Atención
    1.17
     astonishment
    1.16
    Piotr
    1.16
    Activations Density 0.000%

    No Known Activations