© 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. 429
    Prev
    Next
    INDEX
    Explanations

    time notation

    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
    áját
    -1.34
    ρέπει
    -1.09
    IVATE
    -1.09
     Hvordan
    -1.07
    Pesquisa
    -1.06
    othes
    -1.04
     facilite
    -1.03
     introd
    -1.03
     collectons
    -1.02
    AILABILITY
    -1.02
    POSITIVE LOGITS
    ,
    1.20
     even
    1.00
     when
    0.94
    et
    0.91
    .
    0.90
    k
    0.87
     not
    0.85
     and
    0.84
     where
    0.84
    Q
    0.84
    Activations Density 0.004%

    No Known Activations