© 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. 22-GEMMASCOPE-RES-131K
    7. 54390
    Prev
    Next
    INDEX
    Explanations

    different, unusual, atypical

    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
     and
    -1.15
     schließlich
    -1.14
     any
    -1.06
     memudahkan
    -1.05
     then
    -1.00
     easy
    -1.00
     quickly
    -1.00
    ัท
    -0.99
     adequate
    -0.96
     when
    -0.96
    POSITIVE LOGITS
     instead
    2.41
    Instead
    1.88
    instead
    1.82
     вместо
    1.81
     Instead
    1.76
     invece
    1.65
     rather
    1.61
    ではなく
    1.51
     unlike
    1.50
    unlike
    1.44
    Activations Density 0.072%

    No Known Activations