© 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. 115959
    Prev
    Next
    INDEX
    Explanations

    no, not, or without

    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
     both
    -1.95
     некото
    -1.74
     både
    -1.69
     certains
    -1.48
     also
    -1.45
     некоторые
    -1.41
     لكل
    -1.41
     and
    -1.39
    都有
    -1.38
    both
    -1.36
    POSITIVE LOGITS
     either
    4.63
     any
    4.56
     anything
    4.38
     anymore
    3.77
    either
    3.75
     nor
    3.56
    有任何
    3.52
     anyone
    3.48
     anywhere
    3.20
    任何
    3.20
    Activations Density 0.198%

    No Known Activations