© 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. 84269
    Prev
    Next
    INDEX
    Explanations

    special characters and code constructs

    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
     new
    -0.96
     makes
    -0.83
     from
    -0.83
     like
    -0.83
    دى
    -0.81
     reasonably
    -0.80
     not
    -0.79
     had
    -0.77
    蔬菜
    -0.76
     took
    -0.75
    POSITIVE LOGITS
    ceros
    0.92
     luscious
    0.91
    koszulka
    0.85
    ändig
    0.84
    silla
    0.84
     redaktion
    0.84
    readFileSync
    0.82
    centage
    0.82
    (\%)
    0.82
    aceite
    0.81
    Activations Density 0.001%

    No Known Activations