© 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. 124695
    Prev
    Next
    INDEX
    Explanations

    manner, timing, or reason

    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
     for
    -1.93
     to
    -1.87
     that
    -1.74
     at
    -1.51
     again
    -1.35
     from
    -1.31
     would
    -1.27
    EndInit
    -1.15
     wiederum
    -1.14
     instead
    -1.12
    POSITIVE LOGITS
     these
    1.48
     asiática
    1.34
     perché
    1.30
     porque
    1.19
     récomp
    1.19
    羡慕
    1.16
     fragte
    1.16
     financeira
    1.16
    ↵
    1.11
    そも
    1.11
    Activations Density 0.245%

    No Known Activations