© 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. 38081
    Prev
    Next
    INDEX
    Explanations

    ordinal positions or sequences

    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
    ektiv
    -0.96
    hurst
    -0.82
    Pourquoi
    -0.79
    ና
    -0.79
     pelt
    -0.78
     ayudó
    -0.78
     puissiez
    -0.77
    CLUDING
    -0.73
    ULATOR
    -0.71
    🕜
    -0.70
    POSITIVE LOGITS
     bottom
    2.58
     sixth
    2.16
     fifth
    2.13
    bottom
    2.03
     seventh
    2.02
     top
    1.92
     fourth
    1.89
     ninth
    1.84
     eighth
    1.80
    Bottom
    1.77
    Activations Density 0.013%

    No Known Activations