© 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. 102748
    Prev
    Next
    INDEX
    Explanations

    questions that or these

    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
     alté
    -1.45
     meub
    -1.43
     adolescente
    -1.43
     sekunder
    -1.39
     menyen
    -1.34
    ныя
    -1.30
     réfrig
    -1.29
     peluche
    -1.29
     suscit
    -1.28
     pneus
    -1.27
    POSITIVE LOGITS
     these
    1.82
     those
    1.77
     their
    1.66
     now
    1.59
     or
    1.59
     so
    1.45
     like
    1.38
     even
    1.38
     they
    1.34
     what
    1.34
    Activations Density 0.012%

    No Known Activations