© 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. 10-GEMMASCOPE-RES-131K
    7. 9990
    Prev
    Next
    INDEX
    Explanations

    with this

    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
     also
    -2.03
     for
    -2.02
     into
    -1.59
     quite
    -1.55
     takes
    -1.55
     time
    -1.55
     at
    -1.53
     either
    -1.51
    ally
    -1.49
     taking
    -1.49
    POSITIVE LOGITS
    ‘’
    1.43
    malı
    1.42
     AFRICAN
    1.37
     ORANGE
    1.35
     begon
    1.34
     BOSTON
    1.30
    Tiffany
    1.29
    joyed
    1.27
     SUNDAY
    1.26
     MICHIGAN
    1.25
    Activations Density 0.141%

    No Known Activations