© 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. 116606
    Prev
    Next
    INDEX
    Explanations

    time duration and count

    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
    ChildIndex
    -0.85
    天氣
    -0.83
    erunner
    -0.83
    Diversity
    -0.81
     secs
    -0.80
     minta
    -0.79
     traktor
    -0.78
     spou
    -0.78
     köpa
    -0.77
     escolar
    -0.76
    POSITIVE LOGITS
     away
    1.10
     of
    1.06
     ago
    0.84
     bomb
    0.84
     verantwort
    0.81
     lietu
    0.79
    vible
    0.77
     taller
    0.77
    deu
    0.77
     Verfü
    0.75
    Activations Density 0.005%

    No Known Activations