© 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. 34-GEMMASCOPE-RES-131K
    7. 103635
    Prev
    Next
    INDEX
    Explanations

    discovery of historical scientific findings

    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_34/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
     or
    -1.16
     your
    -1.13
    する場合
    -1.10
    錨
    -0.98
     recomendable
    -0.97
    Israël
    -0.94
    があるので
    -0.94
    しなければ
    -0.94
     usually
    -0.93
     postmodern
    -0.93
    POSITIVE LOGITS
     damals
    1.13
    当时
    1.06
     observations
    1.02
    Ή
    1.02
     тогда
    0.99
    當時
    0.99
     beliau
    0.99
     allora
    0.98
    まだ
    0.96
     himself
    0.95
    Activations Density 0.086%

    No Known Activations