© 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. 38029
    Prev
    Next
    INDEX
    Explanations

    helping, combining, to strengthen

    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
     весьма
    -1.37
    beit
    -1.37
     sans
    -1.36
    fucking
    -1.32
    ]^{\
    -1.30
    damn
    -1.27
    literally
    -1.25
     nimmer
    -1.25
    Damn
    -1.24
    如此
    -1.23
    POSITIVE LOGITS
     meistens
    1.90
     because
    1.73
     trotzdem
    1.59
     different
    1.54
     sometimes
    1.47
     careful
    1.43
     helped
    1.41
     helps
    1.41
     chré
    1.41
     worried
    1.41
    Activations Density 0.089%

    No Known Activations