© 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. 33532
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

    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
     in
    -0.88
     takes
    -0.84
     even
    -0.81
    boots
    -0.81
     pelas
    -0.80
    For
    -0.79
     at
    -0.77
     with
    -0.77
    หว
    -0.76
     Dr
    -0.74
    POSITIVE LOGITS
     Saltar
    0.85
    agara
    0.84
    ⚂
    0.83
     gagner
    0.79
    小さく
    0.79
    ٫
    0.79
    红了
    0.79
    hilfe
    0.79
    ωση
    0.78
    🦫
    0.77
    Activations Density 0.063%

    No Known Activations