© 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. 74961
    Prev
    Next
    INDEX
    Explanations

    engineers and professionals

    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
     !!!!
    -1.37
    €™
    -1.22
    having
    -1.20
    ԁ
    -1.20
    within
    -1.16
    those
    -1.16
     foll
    -1.16
     hace
    -1.16
    creating
    -1.14
    many
    -1.13
    POSITIVE LOGITS
     both
    1.76
     probably
    1.41
     gneiss
    1.38
     usually
    1.38
     undoubtedly
    1.30
     seems
    1.29
     promotes
    1.27
     more
    1.25
     and
    1.23
     plastico
    1.22
    Activations Density 0.021%

    No Known Activations