© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67931
    Prev
    Next
    INDEX
    Explanations

    died followed by dates

    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
    lamabad
    -1.51
     musíte
    -1.44
    ఝ
    -1.39
     rhein
    -1.37
    presented
    -1.37
     proposta
    -1.34
     resep
    -1.32
     fortemente
    -1.32
    offering
    -1.31
     problemet
    -1.31
    POSITIVE LOGITS
     by
    2.22
     on
    1.96
     so
    1.78
     after
    1.72
     in
    1.70
     most
    1.60
     from
    1.41
     over
    1.41
     even
    1.39
     IN
    1.38
    Activations Density 0.052%

    No Known Activations