© 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. 70229
    Prev
    Next
    INDEX
    Explanations

    that is / that isn't

    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
     должны
    -1.30
     krijg
    -1.23
    begin
    -1.23
    ">!
    -1.21
    ftar
    -1.20
     также
    -1.19
     نیز
    -1.17
     moeten
    -1.16
    ATELY
    -1.16
     tiež
    -1.16
    POSITIVE LOGITS
     is
    2.36
     has
    1.37
     wasn
    1.31
     isn
    1.24
     was
    1.24
     both
    1.23
     while
    1.23
     other
    1.20
     others
    1.20
     another
    1.19
    Activations Density 0.081%

    No Known Activations