© 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. 65440
    Prev
    Next
    INDEX
    Explanations

    numbers and code snippets

    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
     łyż
    -1.70
    förderung
    -1.63
    乁
    -1.59
    those
    -1.59
     !!!!!
    -1.56
     dà
    -1.48
    maybe
    -1.48
     '',
    -1.47
     pantaloni
    -1.47
     ſever
    -1.46
    POSITIVE LOGITS
     so
    2.50
     while
    2.36
     we
    2.31
     Because
    2.22
     Since
    2.17
     because
    2.11
     a
    2.11
     more
    2.08
     first
    2.05
     when
    2.02
    Activations Density 0.015%

    No Known Activations