Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8610
    Prev
    Next
    INDEX
    Explanations

    contrasting statements

    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
     zwar
    -1.41
     übrigens
    -1.11
    actually
    -1.11
     certes
    -1.09
     кстати
    -1.07
     anzi
    -1.06
    incident
    -1.04
    勿論
    -1.03
    possibly
    -1.01
     fortunately
    -0.98
    POSITIVE LOGITS
     realistically
    1.37
     for
    1.34
     until
    1.28
     honestly
    1.25
    となると
    1.23
    それにしても
    1.23
     then
    1.13
    Given
    1.13
     from
    1.12
     after
    1.12
    Activations Density 0.048%

    No Known Activations