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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 29
    Prev
    Next
    INDEX
    Explanations

    clause initiators

    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
     these
    -1.70
     I
    -1.64
     you
    -1.54
     podremos
    -1.47
     tendremos
    -1.44
     and
    -1.43
     acestui
    -1.43
     is
    -1.41
     acestei
    -1.39
     my
    -1.36
    POSITIVE LOGITS
     to
    1.88
     during
    1.61
    giày
    1.57
     было
    1.48
     casos
    1.46
    tablissements
    1.44
    création
    1.42
    ardı
    1.41
    žit
    1.41
     was
    1.41
    Activations Density 0.159%

    No Known Activations