© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86613
    Prev
    Next
    INDEX
    Explanations

    key-value pairs, code structure

    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
    Since
    -2.00
    Before
    -1.83
    When
    -1.80
     our
    -1.77
    Despite
    -1.73
     with
    -1.71
    Two
    -1.69
    Through
    -1.64
    Although
    -1.64
    While
    -1.62
    POSITIVE LOGITS
     something
    1.71
    튿
    1.59
     chiaramente
    1.47
    苼
    1.47
     confines
    1.41
    ⎔
    1.40
     eventually
    1.38
     doivent
    1.34
     manutenção
    1.34
    でもある
    1.34
    Activations Density 0.041%

    No Known Activations