© 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. 97771
    Prev
    Next
    INDEX
    Explanations

    concepts followed by verbs

    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
     будут
    -1.27
     miatt
    -1.25
    étaient
    -1.25
    believe
    -1.22
     занимает
    -1.20
     voltak
    -1.16
     vannak
    -1.16
    varies
    -1.13
     приводит
    -1.09
     hadden
    -1.09
    POSITIVE LOGITS
     is
    2.47
     cannot
    2.42
     must
    1.84
     can
    1.61
     does
    1.39
     never
    1.37
     merely
    1.36
     Cannot
    1.31
     too
    1.29
     only
    1.28
    Activations Density 0.073%

    No Known Activations