© 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. 34-GEMMASCOPE-RES-131K
    4. 34950
    Prev
    Next
    INDEX
    Explanations

    see you there

    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
     dagens
    -1.16
     this
    -1.14
     now
    -1.10
     it
    -1.09
     adesso
    -1.05
     its
    -1.04
     oggi
    -1.03
     stedet
    -1.03
     today
    -1.02
     aujourd
    -0.98
    POSITIVE LOGITS
     on
    1.29
     at
    1.23
     soon
    1.22
     again
    1.21
     in
    1.14
     around
    1.09
    熜
    0.99
    topRight
    0.97
     there
    0.94
     entonces
    0.94
    Activations Density 0.006%

    No Known Activations