© 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. 10-GEMMASCOPE-RES-131K
    7. 123857
    Prev
    Next
    INDEX
    Explanations

    common introductory phrases

    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_10/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
     it
    -1.70
     then
    -1.69
     they
    -1.61
     of
    -1.51
     possibilità
    -1.45
     inimes
    -1.41
     wrze
    -1.41
    袛
    -1.40
     beserta
    -1.36
     pö
    -1.34
    POSITIVE LOGITS
     tantôt
    1.42
    ’
    1.30
    われています
    1.26
    藓
    1.25
     рады
    1.25
    aA
    1.25
     mostró
    1.23
     itself
    1.23
     volverá
    1.22
     sintió
    1.22
    Activations Density 0.068%

    No Known Activations