© 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. 45609
    Prev
    Next
    INDEX
    Explanations

    future expectations and outcomes

    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
    sometimes
    -1.40
     telah
    -1.26
     sometimes
    -1.19
     spesso
    -1.18
     schein
    -1.16
    seem
    -1.13
     parfois
    -1.13
     apparently
    -1.09
     đã
    -1.09
     supposed
    -1.07
    POSITIVE LOGITS
     soon
    2.16
     will
    1.71
     be
    1.66
     become
    1.46
     eventually
    1.41
    很快
    1.30
    soon
    1.23
     Soon
    1.18
     end
    1.15
     sớm
    1.14
    Activations Density 0.071%

    No Known Activations